Compare commits
2 Commits
f415a8ef19
...
6137f53c38
| Author | SHA1 | Date |
|---|---|---|
 李光春
|
6137f53c38 | 12 months ago |
|
李光春
|
003f87b4d7 | 1 year ago |
@ -1,5 +1,5 @@
|
||||
package go_library
|
||||
|
||||
func Version() string {
|
||||
return "1.0.147"
|
||||
return "1.0.148"
|
||||
}
|
||||
|
||||
@ -0,0 +1,32 @@
|
||||
package goip
|
||||
|
||||
import (
|
||||
"github.com/dtapps/go-library/utils/goip/geoip"
|
||||
"github.com/dtapps/go-library/utils/goip/ip2region"
|
||||
"github.com/dtapps/go-library/utils/goip/ip2region_v2"
|
||||
"github.com/dtapps/go-library/utils/goip/ipv6wry"
|
||||
"github.com/dtapps/go-library/utils/goip/qqwry"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestV4OnlineDownload(t *testing.T) {
|
||||
qqwry.OnlineDownload()
|
||||
}
|
||||
|
||||
func TestV6OnlineDownload(t *testing.T) {
|
||||
ipv6wry.OnlineDownload()
|
||||
}
|
||||
|
||||
func TestIp2regionOnlineDownload(t *testing.T) {
|
||||
ip2region.OnlineDownload()
|
||||
}
|
||||
|
||||
func TestIp2regionV2OnlineDownload(t *testing.T) {
|
||||
ip2region_v2.OnlineDownload()
|
||||
}
|
||||
|
||||
func TestGeoIpOnlineDownload(t *testing.T) {
|
||||
geoip.OnlineDownload(geoip.GetGeoLite2CountryDownloadUrl("bb26plSFSVqDCJen"), "GeoLite2-Country_20230602.tar.gz")
|
||||
geoip.OnlineDownload(geoip.GetGeoLite2CityDownloadUrl("bb26plSFSVqDCJen"), "GeoLite2-City_20230602.tar.gz")
|
||||
geoip.OnlineDownload(geoip.GetGeoLite2AsnDownloadUrl("bb26plSFSVqDCJen"), "GeoLite2-ASN_20230602.tar.gz")
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 69 MiB After Width: | Height: | Size: 68 MiB |
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 85 KiB |
|
Before Width: | Height: | Size: 86 KiB |
@ -0,0 +1,66 @@
|
||||
// +build amd64,go1.15,!go1.21
|
||||
|
||||
/*
|
||||
* Copyright 2023 ByteDance Inc.
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package decoder
|
||||
|
||||
import (
|
||||
`github.com/bytedance/sonic/internal/decoder`
|
||||
)
|
||||
|
||||
// Decoder is the decoder context object
|
||||
type Decoder = decoder.Decoder
|
||||
|
||||
type MismatchTypeError = decoder.MismatchTypeError
|
||||
|
||||
// Options for decode.
|
||||
type Options = decoder.Options
|
||||
|
||||
const (
|
||||
OptionUseInt64 Options = decoder.OptionUseInt64
|
||||
OptionUseNumber Options = decoder.OptionUseNumber
|
||||
OptionUseUnicodeErrors Options = decoder.OptionUseUnicodeErrors
|
||||
OptionDisableUnknown Options = decoder.OptionDisableUnknown
|
||||
OptionCopyString Options = decoder.OptionCopyString
|
||||
OptionValidateString Options = decoder.OptionValidateString
|
||||
)
|
||||
|
||||
// StreamDecoder is the decoder context object for streaming input.
|
||||
type StreamDecoder = decoder.StreamDecoder
|
||||
|
||||
type SyntaxError = decoder.SyntaxError
|
||||
|
||||
var (
|
||||
// NewDecoder creates a new decoder instance.
|
||||
NewDecoder = decoder.NewDecoder
|
||||
|
||||
// NewStreamDecoder adapts to encoding/json.NewDecoder API.
|
||||
//
|
||||
// NewStreamDecoder returns a new decoder that reads from r.
|
||||
NewStreamDecoder = decoder.NewStreamDecoder
|
||||
|
||||
// Pretouch compiles vt ahead-of-time to avoid JIT compilation on-the-fly, in
|
||||
// order to reduce the first-hit latency.
|
||||
//
|
||||
// Opts are the compile options, for example, "option.WithCompileRecursiveDepth" is
|
||||
// a compile option to set the depth of recursive compile for the nested struct type.
|
||||
Pretouch = decoder.Pretouch
|
||||
|
||||
// Skip skips only one json value, and returns first non-blank character position and its ending position if it is valid.
|
||||
// Otherwise, returns negative error code using start and invalid character position using end
|
||||
Skip = decoder.Skip
|
||||
)
|
||||
@ -0,0 +1,196 @@
|
||||
// +build !amd64 go1.21
|
||||
|
||||
/*
|
||||
* Copyright 2023 ByteDance Inc.
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package decoder
|
||||
|
||||
import (
|
||||
`encoding/json`
|
||||
`bytes`
|
||||
`reflect`
|
||||
`github.com/bytedance/sonic/internal/native/types`
|
||||
`github.com/bytedance/sonic/option`
|
||||
`io`
|
||||
)
|
||||
|
||||
const (
|
||||
_F_use_int64 = iota
|
||||
_F_use_number
|
||||
_F_disable_urc
|
||||
_F_disable_unknown
|
||||
_F_copy_string
|
||||
_F_validate_string
|
||||
|
||||
_F_allow_control = 31
|
||||
)
|
||||
|
||||
type Options uint64
|
||||
|
||||
const (
|
||||
OptionUseInt64 Options = 1 << _F_use_int64
|
||||
OptionUseNumber Options = 1 << _F_use_number
|
||||
OptionUseUnicodeErrors Options = 1 << _F_disable_urc
|
||||
OptionDisableUnknown Options = 1 << _F_disable_unknown
|
||||
OptionCopyString Options = 1 << _F_copy_string
|
||||
OptionValidateString Options = 1 << _F_validate_string
|
||||
)
|
||||
|
||||
func (self *Decoder) SetOptions(opts Options) {
|
||||
if (opts & OptionUseNumber != 0) && (opts & OptionUseInt64 != 0) {
|
||||
panic("can't set OptionUseInt64 and OptionUseNumber both!")
|
||||
}
|
||||
self.f = uint64(opts)
|
||||
}
|
||||
|
||||
|
||||
// Decoder is the decoder context object
|
||||
type Decoder struct {
|
||||
i int
|
||||
f uint64
|
||||
s string
|
||||
}
|
||||
|
||||
// NewDecoder creates a new decoder instance.
|
||||
func NewDecoder(s string) *Decoder {
|
||||
return &Decoder{s: s}
|
||||
}
|
||||
|
||||
// Pos returns the current decoding position.
|
||||
func (self *Decoder) Pos() int {
|
||||
return self.i
|
||||
}
|
||||
|
||||
func (self *Decoder) Reset(s string) {
|
||||
self.s = s
|
||||
self.i = 0
|
||||
// self.f = 0
|
||||
}
|
||||
|
||||
// NOTE: api fallback do nothing
|
||||
func (self *Decoder) CheckTrailings() error {
|
||||
pos := self.i
|
||||
buf := self.s
|
||||
/* skip all the trailing spaces */
|
||||
if pos != len(buf) {
|
||||
for pos < len(buf) && (types.SPACE_MASK & (1 << buf[pos])) != 0 {
|
||||
pos++
|
||||
}
|
||||
}
|
||||
|
||||
/* then it must be at EOF */
|
||||
if pos == len(buf) {
|
||||
return nil
|
||||
}
|
||||
|
||||
/* junk after JSON value */
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
// Decode parses the JSON-encoded data from current position and stores the result
|
||||
// in the value pointed to by val.
|
||||
func (self *Decoder) Decode(val interface{}) error {
|
||||
r := bytes.NewBufferString(self.s)
|
||||
dec := json.NewDecoder(r)
|
||||
if (self.f | uint64(OptionUseNumber)) != 0 {
|
||||
dec.UseNumber()
|
||||
}
|
||||
if (self.f | uint64(OptionDisableUnknown)) != 0 {
|
||||
dec.DisallowUnknownFields()
|
||||
}
|
||||
return dec.Decode(val)
|
||||
}
|
||||
|
||||
// UseInt64 indicates the Decoder to unmarshal an integer into an interface{} as an
|
||||
// int64 instead of as a float64.
|
||||
func (self *Decoder) UseInt64() {
|
||||
self.f |= 1 << _F_use_int64
|
||||
self.f &^= 1 << _F_use_number
|
||||
}
|
||||
|
||||
// UseNumber indicates the Decoder to unmarshal a number into an interface{} as a
|
||||
// json.Number instead of as a float64.
|
||||
func (self *Decoder) UseNumber() {
|
||||
self.f &^= 1 << _F_use_int64
|
||||
self.f |= 1 << _F_use_number
|
||||
}
|
||||
|
||||
// UseUnicodeErrors indicates the Decoder to return an error when encounter invalid
|
||||
// UTF-8 escape sequences.
|
||||
func (self *Decoder) UseUnicodeErrors() {
|
||||
self.f |= 1 << _F_disable_urc
|
||||
}
|
||||
|
||||
// DisallowUnknownFields indicates the Decoder to return an error when the destination
|
||||
// is a struct and the input contains object keys which do not match any
|
||||
// non-ignored, exported fields in the destination.
|
||||
func (self *Decoder) DisallowUnknownFields() {
|
||||
self.f |= 1 << _F_disable_unknown
|
||||
}
|
||||
|
||||
// CopyString indicates the Decoder to decode string values by copying instead of referring.
|
||||
func (self *Decoder) CopyString() {
|
||||
self.f |= 1 << _F_copy_string
|
||||
}
|
||||
|
||||
// ValidateString causes the Decoder to validate string values when decoding string value
|
||||
// in JSON. Validation is that, returning error when unescaped control chars(0x00-0x1f) or
|
||||
// invalid UTF-8 chars in the string value of JSON.
|
||||
func (self *Decoder) ValidateString() {
|
||||
self.f |= 1 << _F_validate_string
|
||||
}
|
||||
|
||||
// Pretouch compiles vt ahead-of-time to avoid JIT compilation on-the-fly, in
|
||||
// order to reduce the first-hit latency.
|
||||
//
|
||||
// Opts are the compile options, for example, "option.WithCompileRecursiveDepth" is
|
||||
// a compile option to set the depth of recursive compile for the nested struct type.
|
||||
func Pretouch(vt reflect.Type, opts ...option.CompileOption) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
type StreamDecoder struct {
|
||||
r io.Reader
|
||||
buf []byte
|
||||
scanp int
|
||||
scanned int64
|
||||
err error
|
||||
Decoder
|
||||
}
|
||||
|
||||
// NewStreamDecoder adapts to encoding/json.NewDecoder API.
|
||||
//
|
||||
// NewStreamDecoder returns a new decoder that reads from r.
|
||||
func NewStreamDecoder(r io.Reader) *StreamDecoder {
|
||||
return &StreamDecoder{r : r}
|
||||
}
|
||||
|
||||
// Decode decodes input stream into val with corresponding data.
|
||||
// Redundantly bytes may be read and left in its buffer, and can be used at next call.
|
||||
// Either io error from underlying io.Reader (except io.EOF)
|
||||
// or syntax error from data will be recorded and stop subsequently decoding.
|
||||
func (self *StreamDecoder) Decode(val interface{}) (err error) {
|
||||
dec := json.NewDecoder(self.r)
|
||||
if (self.f | uint64(OptionUseNumber)) != 0 {
|
||||
dec.UseNumber()
|
||||
}
|
||||
if (self.f | uint64(OptionDisableUnknown)) != 0 {
|
||||
dec.DisallowUnknownFields()
|
||||
}
|
||||
return dec.Decode(val)
|
||||
}
|
||||
|
||||
@ -0,0 +1,108 @@
|
||||
// +build amd64,go1.15,!go1.21
|
||||
|
||||
/*
|
||||
* Copyright 2023 ByteDance Inc.
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package encoder
|
||||
|
||||
import (
|
||||
`github.com/bytedance/sonic/internal/encoder`
|
||||
)
|
||||
|
||||
|
||||
// Encoder represents a specific set of encoder configurations.
|
||||
type Encoder = encoder.Encoder
|
||||
|
||||
// StreamEncoder uses io.Writer as input.
|
||||
type StreamEncoder = encoder.StreamEncoder
|
||||
|
||||
// Options is a set of encoding options.
|
||||
type Options = encoder.Options
|
||||
|
||||
const (
|
||||
// SortMapKeys indicates that the keys of a map needs to be sorted
|
||||
// before serializing into JSON.
|
||||
// WARNING: This hurts performance A LOT, USE WITH CARE.
|
||||
SortMapKeys Options = encoder.SortMapKeys
|
||||
|
||||
// EscapeHTML indicates encoder to escape all HTML characters
|
||||
// after serializing into JSON (see https://pkg.go.dev/encoding/json#HTMLEscape).
|
||||
// WARNING: This hurts performance A LOT, USE WITH CARE.
|
||||
EscapeHTML Options = encoder.EscapeHTML
|
||||
|
||||
// CompactMarshaler indicates that the output JSON from json.Marshaler
|
||||
// is always compact and needs no validation
|
||||
CompactMarshaler Options = encoder.CompactMarshaler
|
||||
|
||||
// NoQuoteTextMarshaler indicates that the output text from encoding.TextMarshaler
|
||||
// is always escaped string and needs no quoting
|
||||
NoQuoteTextMarshaler Options = encoder.NoQuoteTextMarshaler
|
||||
|
||||
// NoNullSliceOrMap indicates all empty Array or Object are encoded as '[]' or '{}',
|
||||
// instead of 'null'
|
||||
NoNullSliceOrMap Options = encoder.NoNullSliceOrMap
|
||||
|
||||
// ValidateString indicates that encoder should validate the input string
|
||||
// before encoding it into JSON.
|
||||
ValidateString Options = encoder.ValidateString
|
||||
|
||||
// CompatibleWithStd is used to be compatible with std encoder.
|
||||
CompatibleWithStd Options = encoder.CompatibleWithStd
|
||||
)
|
||||
|
||||
|
||||
var (
|
||||
// Encode returns the JSON encoding of val, encoded with opts.
|
||||
Encode = encoder.Encode
|
||||
|
||||
// EncodeInto is like Encode but uses a user-supplied buffer instead of allocating a new one.
|
||||
EncodeIndented = encoder.EncodeIndented
|
||||
|
||||
// EncodeIndented is like Encode but applies Indent to format the output.
|
||||
// Each JSON element in the output will begin on a new line beginning with prefix
|
||||
// followed by one or more copies of indent according to the indentation nesting.
|
||||
EncodeInto = encoder.EncodeInto
|
||||
|
||||
// HTMLEscape appends to dst the JSON-encoded src with <, >, &, U+2028 and U+2029
|
||||
// characters inside string literals changed to \u003c, \u003e, \u0026, \u2028, \u2029
|
||||
// so that the JSON will be safe to embed inside HTML <script> tags.
|
||||
// For historical reasons, web browsers don't honor standard HTML
|
||||
// escaping within <script> tags, so an alternative JSON encoding must
|
||||
// be used.
|
||||
HTMLEscape = encoder.HTMLEscape
|
||||
|
||||
// Pretouch compiles vt ahead-of-time to avoid JIT compilation on-the-fly, in
|
||||
// order to reduce the first-hit latency.
|
||||
//
|
||||
// Opts are the compile options, for example, "option.WithCompileRecursiveDepth" is
|
||||
// a compile option to set the depth of recursive compile for the nested struct type.
|
||||
Pretouch = encoder.Pretouch
|
||||
|
||||
// Quote returns the JSON-quoted version of s.
|
||||
Quote = encoder.Quote
|
||||
|
||||
// Valid validates json and returns first non-blank character position,
|
||||
// if it is only one valid json value.
|
||||
// Otherwise returns invalid character position using start.
|
||||
//
|
||||
// Note: it does not check for the invalid UTF-8 characters.
|
||||
Valid = encoder.Valid
|
||||
|
||||
// NewStreamEncoder adapts to encoding/json.NewDecoder API.
|
||||
//
|
||||
// NewStreamEncoder returns a new encoder that write to w.
|
||||
NewStreamEncoder = encoder.NewStreamEncoder
|
||||
)
|
||||
@ -0,0 +1,234 @@
|
||||
// +build !amd64 go1.21
|
||||
|
||||
/*
|
||||
* Copyright 2023 ByteDance Inc.
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package encoder
|
||||
|
||||
import (
|
||||
`io`
|
||||
`bytes`
|
||||
`encoding/json`
|
||||
`reflect`
|
||||
|
||||
`github.com/bytedance/sonic/option`
|
||||
)
|
||||
|
||||
// Options is a set of encoding options.
|
||||
type Options uint64
|
||||
|
||||
const (
|
||||
bitSortMapKeys = iota
|
||||
bitEscapeHTML
|
||||
bitCompactMarshaler
|
||||
bitNoQuoteTextMarshaler
|
||||
bitNoNullSliceOrMap
|
||||
bitValidateString
|
||||
|
||||
// used for recursive compile
|
||||
bitPointerValue = 63
|
||||
)
|
||||
|
||||
const (
|
||||
// SortMapKeys indicates that the keys of a map needs to be sorted
|
||||
// before serializing into JSON.
|
||||
// WARNING: This hurts performance A LOT, USE WITH CARE.
|
||||
SortMapKeys Options = 1 << bitSortMapKeys
|
||||
|
||||
// EscapeHTML indicates encoder to escape all HTML characters
|
||||
// after serializing into JSON (see https://pkg.go.dev/encoding/json#HTMLEscape).
|
||||
// WARNING: This hurts performance A LOT, USE WITH CARE.
|
||||
EscapeHTML Options = 1 << bitEscapeHTML
|
||||
|
||||
// CompactMarshaler indicates that the output JSON from json.Marshaler
|
||||
// is always compact and needs no validation
|
||||
CompactMarshaler Options = 1 << bitCompactMarshaler
|
||||
|
||||
// NoQuoteTextMarshaler indicates that the output text from encoding.TextMarshaler
|
||||
// is always escaped string and needs no quoting
|
||||
NoQuoteTextMarshaler Options = 1 << bitNoQuoteTextMarshaler
|
||||
|
||||
// NoNullSliceOrMap indicates all empty Array or Object are encoded as '[]' or '{}',
|
||||
// instead of 'null'
|
||||
NoNullSliceOrMap Options = 1 << bitNoNullSliceOrMap
|
||||
|
||||
// ValidateString indicates that encoder should validate the input string
|
||||
// before encoding it into JSON.
|
||||
ValidateString Options = 1 << bitValidateString
|
||||
|
||||
// CompatibleWithStd is used to be compatible with std encoder.
|
||||
CompatibleWithStd Options = SortMapKeys | EscapeHTML | CompactMarshaler
|
||||
)
|
||||
|
||||
// Encoder represents a specific set of encoder configurations.
|
||||
type Encoder struct {
|
||||
Opts Options
|
||||
prefix string
|
||||
indent string
|
||||
}
|
||||
|
||||
// Encode returns the JSON encoding of v.
|
||||
func (self *Encoder) Encode(v interface{}) ([]byte, error) {
|
||||
if self.indent != "" || self.prefix != "" {
|
||||
return EncodeIndented(v, self.prefix, self.indent, self.Opts)
|
||||
}
|
||||
return Encode(v, self.Opts)
|
||||
}
|
||||
|
||||
// SortKeys enables the SortMapKeys option.
|
||||
func (self *Encoder) SortKeys() *Encoder {
|
||||
self.Opts |= SortMapKeys
|
||||
return self
|
||||
}
|
||||
|
||||
// SetEscapeHTML specifies if option EscapeHTML opens
|
||||
func (self *Encoder) SetEscapeHTML(f bool) {
|
||||
if f {
|
||||
self.Opts |= EscapeHTML
|
||||
} else {
|
||||
self.Opts &= ^EscapeHTML
|
||||
}
|
||||
}
|
||||
|
||||
// SetValidateString specifies if option ValidateString opens
|
||||
func (self *Encoder) SetValidateString(f bool) {
|
||||
if f {
|
||||
self.Opts |= ValidateString
|
||||
} else {
|
||||
self.Opts &= ^ValidateString
|
||||
}
|
||||
}
|
||||
|
||||
// SetCompactMarshaler specifies if option CompactMarshaler opens
|
||||
func (self *Encoder) SetCompactMarshaler(f bool) {
|
||||
if f {
|
||||
self.Opts |= CompactMarshaler
|
||||
} else {
|
||||
self.Opts &= ^CompactMarshaler
|
||||
}
|
||||
}
|
||||
|
||||
// SetNoQuoteTextMarshaler specifies if option NoQuoteTextMarshaler opens
|
||||
func (self *Encoder) SetNoQuoteTextMarshaler(f bool) {
|
||||
if f {
|
||||
self.Opts |= NoQuoteTextMarshaler
|
||||
} else {
|
||||
self.Opts &= ^NoQuoteTextMarshaler
|
||||
}
|
||||
}
|
||||
|
||||
// SetIndent instructs the encoder to format each subsequent encoded
|
||||
// value as if indented by the package-level function EncodeIndent().
|
||||
// Calling SetIndent("", "") disables indentation.
|
||||
func (enc *Encoder) SetIndent(prefix, indent string) {
|
||||
enc.prefix = prefix
|
||||
enc.indent = indent
|
||||
}
|
||||
|
||||
// Quote returns the JSON-quoted version of s.
|
||||
func Quote(s string) string {
|
||||
/* check for empty string */
|
||||
if s == "" {
|
||||
return `""`
|
||||
}
|
||||
|
||||
out, _ := json.Marshal(s)
|
||||
return string(out)
|
||||
}
|
||||
|
||||
// Encode returns the JSON encoding of val, encoded with opts.
|
||||
func Encode(val interface{}, opts Options) ([]byte, error) {
|
||||
return json.Marshal(val)
|
||||
}
|
||||
|
||||
// EncodeInto is like Encode but uses a user-supplied buffer instead of allocating
|
||||
// a new one.
|
||||
func EncodeInto(buf *[]byte, val interface{}, opts Options) error {
|
||||
if buf == nil {
|
||||
panic("user-supplied buffer buf is nil")
|
||||
}
|
||||
w := bytes.NewBuffer(*buf)
|
||||
enc := json.NewEncoder(w)
|
||||
enc.SetEscapeHTML((opts & EscapeHTML) != 0)
|
||||
err := enc.Encode(val)
|
||||
*buf = w.Bytes()
|
||||
return err
|
||||
}
|
||||
|
||||
// HTMLEscape appends to dst the JSON-encoded src with <, >, &, U+2028 and U+2029
|
||||
// characters inside string literals changed to \u003c, \u003e, \u0026, \u2028, \u2029
|
||||
// so that the JSON will be safe to embed inside HTML <script> tags.
|
||||
// For historical reasons, web browsers don't honor standard HTML
|
||||
// escaping within <script> tags, so an alternative JSON encoding must
|
||||
// be used.
|
||||
func HTMLEscape(dst []byte, src []byte) []byte {
|
||||
d := bytes.NewBuffer(dst)
|
||||
json.HTMLEscape(d, src)
|
||||
return d.Bytes()
|
||||
}
|
||||
|
||||
// EncodeIndented is like Encode but applies Indent to format the output.
|
||||
// Each JSON element in the output will begin on a new line beginning with prefix
|
||||
// followed by one or more copies of indent according to the indentation nesting.
|
||||
func EncodeIndented(val interface{}, prefix string, indent string, opts Options) ([]byte, error) {
|
||||
w := bytes.NewBuffer([]byte{})
|
||||
enc := json.NewEncoder(w)
|
||||
enc.SetEscapeHTML((opts & EscapeHTML) != 0)
|
||||
enc.SetIndent(prefix, indent)
|
||||
err := enc.Encode(val)
|
||||
out := w.Bytes()
|
||||
return out, err
|
||||
}
|
||||
|
||||
// Pretouch compiles vt ahead-of-time to avoid JIT compilation on-the-fly, in
|
||||
// order to reduce the first-hit latency.
|
||||
//
|
||||
// Opts are the compile options, for example, "option.WithCompileRecursiveDepth" is
|
||||
// a compile option to set the depth of recursive compile for the nested struct type.
|
||||
func Pretouch(vt reflect.Type, opts ...option.CompileOption) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Valid validates json and returns first non-blank character position,
|
||||
// if it is only one valid json value.
|
||||
// Otherwise returns invalid character position using start.
|
||||
//
|
||||
// Note: it does not check for the invalid UTF-8 characters.
|
||||
func Valid(data []byte) (ok bool, start int) {
|
||||
return json.Valid(data), 0
|
||||
}
|
||||
|
||||
// StreamEncoder uses io.Writer as
|
||||
type StreamEncoder struct {
|
||||
w io.Writer
|
||||
Encoder
|
||||
}
|
||||
|
||||
// NewStreamEncoder adapts to encoding/json.NewDecoder API.
|
||||
//
|
||||
// NewStreamEncoder returns a new encoder that write to w.
|
||||
func NewStreamEncoder(w io.Writer) *StreamEncoder {
|
||||
return &StreamEncoder{w: w}
|
||||
}
|
||||
|
||||
// Encode encodes interface{} as JSON to io.Writer
|
||||
func (enc *StreamEncoder) Encode(val interface{}) (err error) {
|
||||
jenc := json.NewEncoder(enc.w)
|
||||
jenc.SetEscapeHTML((enc.Opts & EscapeHTML) != 0)
|
||||
jenc.SetIndent(enc.prefix, enc.indent)
|
||||
err = jenc.Encode(val)
|
||||
return err
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
Before Width: | Height: | Size: 56 KiB |
|
Before Width: | Height: | Size: 66 KiB |
|
Before Width: | Height: | Size: 94 KiB |
@ -0,0 +1 @@
|
||||
testdata/* linguist-vendored
|
||||
@ -0,0 +1,76 @@
|
||||
# Contributor Covenant Code of Conduct
|
||||
|
||||
## Our Pledge
|
||||
|
||||
In the interest of fostering an open and welcoming environment, we as
|
||||
contributors and maintainers pledge to making participation in our project and
|
||||
our community a harassment-free experience for everyone, regardless of age, body
|
||||
size, disability, ethnicity, sex characteristics, gender identity and expression,
|
||||
level of experience, education, socio-economic status, nationality, personal
|
||||
appearance, race, religion, or sexual identity and orientation.
|
||||
|
||||
## Our Standards
|
||||
|
||||
Examples of behavior that contributes to creating a positive environment
|
||||
include:
|
||||
|
||||
* Using welcoming and inclusive language
|
||||
* Being respectful of differing viewpoints and experiences
|
||||
* Gracefully accepting constructive criticism
|
||||
* Focusing on what is best for the community
|
||||
* Showing empathy towards other community members
|
||||
|
||||
Examples of unacceptable behavior by participants include:
|
||||
|
||||
* The use of sexualized language or imagery and unwelcome sexual attention or
|
||||
advances
|
||||
* Trolling, insulting/derogatory comments, and personal or political attacks
|
||||
* Public or private harassment
|
||||
* Publishing others' private information, such as a physical or electronic
|
||||
address, without explicit permission
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Our Responsibilities
|
||||
|
||||
Project maintainers are responsible for clarifying the standards of acceptable
|
||||
behavior and are expected to take appropriate and fair corrective action in
|
||||
response to any instances of unacceptable behavior.
|
||||
|
||||
Project maintainers have the right and responsibility to remove, edit, or
|
||||
reject comments, commits, code, wiki edits, issues, and other contributions
|
||||
that are not aligned to this Code of Conduct, or to ban temporarily or
|
||||
permanently any contributor for other behaviors that they deem inappropriate,
|
||||
threatening, offensive, or harmful.
|
||||
|
||||
## Scope
|
||||
|
||||
This Code of Conduct applies both within project spaces and in public spaces
|
||||
when an individual is representing the project or its community. Examples of
|
||||
representing a project or community include using an official project e-mail
|
||||
address, posting via an official social media account, or acting as an appointed
|
||||
representative at an online or offline event. Representation of a project may be
|
||||
further defined and clarified by project maintainers.
|
||||
|
||||
## Enforcement
|
||||
|
||||
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
||||
reported by contacting the project team at vasile.gabriel@email.com. All
|
||||
complaints will be reviewed and investigated and will result in a response that
|
||||
is deemed necessary and appropriate to the circumstances. The project team is
|
||||
obligated to maintain confidentiality with regard to the reporter of an incident.
|
||||
Further details of specific enforcement policies may be posted separately.
|
||||
|
||||
Project maintainers who do not follow or enforce the Code of Conduct in good
|
||||
faith may face temporary or permanent repercussions as determined by other
|
||||
members of the project's leadership.
|
||||
|
||||
## Attribution
|
||||
|
||||
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
||||
available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
|
||||
For answers to common questions about this code of conduct, see
|
||||
https://www.contributor-covenant.org/faq
|
||||
@ -0,0 +1,12 @@
|
||||
## Contribute
|
||||
Contributions to **mimetype** are welcome. If you find an issue and you consider
|
||||
contributing, you can use the [Github issues tracker](https://github.com/gabriel-vasile/mimetype/issues)
|
||||
in order to report it, or better yet, open a pull request.
|
||||
|
||||
Code contributions must respect these rules:
|
||||
- code must be test covered
|
||||
- code must be formatted using gofmt tool
|
||||
- exported names must be documented
|
||||
|
||||
**Important**: By submitting a pull request, you agree to allow the project
|
||||
owner to license your work under the same license as that used by the project.
|
||||
@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2018-2020 Gabriel Vasile
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
@ -0,0 +1,108 @@
|
||||
<h1 align="center">
|
||||
mimetype
|
||||
</h1>
|
||||
|
||||
<h4 align="center">
|
||||
A package for detecting MIME types and extensions based on magic numbers
|
||||
</h4>
|
||||
<h6 align="center">
|
||||
Goroutine safe, extensible, no C bindings
|
||||
</h6>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://travis-ci.org/gabriel-vasile/mimetype">
|
||||
<img alt="Build Status" src="https://travis-ci.org/gabriel-vasile/mimetype.svg?branch=master">
|
||||
</a>
|
||||
<a href="https://pkg.go.dev/github.com/gabriel-vasile/mimetype">
|
||||
<img alt="Go Reference" src="https://pkg.go.dev/badge/github.com/gabriel-vasile/mimetype.svg">
|
||||
</a>
|
||||
<a href="https://goreportcard.com/report/github.com/gabriel-vasile/mimetype">
|
||||
<img alt="Go report card" src="https://goreportcard.com/badge/github.com/gabriel-vasile/mimetype">
|
||||
</a>
|
||||
<a href="https://codecov.io/gh/gabriel-vasile/mimetype">
|
||||
<img alt="Code coverage" src="https://codecov.io/gh/gabriel-vasile/mimetype/branch/master/graph/badge.svg?token=qcfJF1kkl2"/>
|
||||
</a>
|
||||
<a href="LICENSE">
|
||||
<img alt="License" src="https://img.shields.io/badge/License-MIT-green.svg">
|
||||
</a>
|
||||
</p>
|
||||
|
||||
## Features
|
||||
- fast and precise MIME type and file extension detection
|
||||
- long list of [supported MIME types](supported_mimes.md)
|
||||
- possibility to [extend](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#example-package-Extend) with other file formats
|
||||
- common file formats are prioritized
|
||||
- [text vs. binary files differentiation](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#example-package-TextVsBinary)
|
||||
- safe for concurrent usage
|
||||
|
||||
## Install
|
||||
```bash
|
||||
go get github.com/gabriel-vasile/mimetype
|
||||
```
|
||||
|
||||
## Usage
|
||||
```go
|
||||
mtype := mimetype.Detect([]byte)
|
||||
// OR
|
||||
mtype, err := mimetype.DetectReader(io.Reader)
|
||||
// OR
|
||||
mtype, err := mimetype.DetectFile("/path/to/file")
|
||||
fmt.Println(mtype.String(), mtype.Extension())
|
||||
```
|
||||
See the [runnable Go Playground examples](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#pkg-overview).
|
||||
|
||||
## Usage'
|
||||
Only use libraries like **mimetype** as a last resort. Content type detection
|
||||
using magic numbers is slow, inaccurate, and non-standard. Most of the times
|
||||
protocols have methods for specifying such metadata; e.g., `Content-Type` header
|
||||
in HTTP and SMTP.
|
||||
|
||||
## FAQ
|
||||
Q: My file is in the list of [supported MIME types](supported_mimes.md) but
|
||||
it is not correctly detected. What should I do?
|
||||
|
||||
A: Some file formats (often Microsoft Office documents) keep their signatures
|
||||
towards the end of the file. Try increasing the number of bytes used for detection
|
||||
with:
|
||||
```go
|
||||
mimetype.SetLimit(1024*1024) // Set limit to 1MB.
|
||||
// or
|
||||
mimetype.SetLimit(0) // No limit, whole file content used.
|
||||
mimetype.DetectFile("file.doc")
|
||||
```
|
||||
If increasing the limit does not help, please
|
||||
[open an issue](https://github.com/gabriel-vasile/mimetype/issues/new?assignees=&labels=&template=mismatched-mime-type-detected.md&title=).
|
||||
|
||||
## Structure
|
||||
**mimetype** uses a hierarchical structure to keep the MIME type detection logic.
|
||||
This reduces the number of calls needed for detecting the file type. The reason
|
||||
behind this choice is that there are file formats used as containers for other
|
||||
file formats. For example, Microsoft Office files are just zip archives,
|
||||
containing specific metadata files. Once a file has been identified as a
|
||||
zip, there is no need to check if it is a text file, but it is worth checking if
|
||||
it is an Microsoft Office file.
|
||||
|
||||
To prevent loading entire files into memory, when detecting from a
|
||||
[reader](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#DetectReader)
|
||||
or from a [file](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#DetectFile)
|
||||
**mimetype** limits itself to reading only the header of the input.
|
||||
<div align="center">
|
||||
<img alt="structure" src="https://github.com/gabriel-vasile/mimetype/blob/420a05228c6a6efbb6e6f080168a25663414ff36/mimetype.gif?raw=true" width="88%">
|
||||
</div>
|
||||
|
||||
## Performance
|
||||
Thanks to the hierarchical structure, searching for common formats first,
|
||||
and limiting itself to file headers, **mimetype** matches the performance of
|
||||
stdlib `http.DetectContentType` while outperforming the alternative package.
|
||||
|
||||
```bash
|
||||
mimetype http.DetectContentType filetype
|
||||
BenchmarkMatchTar-24 250 ns/op 400 ns/op 3778 ns/op
|
||||
BenchmarkMatchZip-24 524 ns/op 351 ns/op 4884 ns/op
|
||||
BenchmarkMatchJpeg-24 103 ns/op 228 ns/op 839 ns/op
|
||||
BenchmarkMatchGif-24 139 ns/op 202 ns/op 751 ns/op
|
||||
BenchmarkMatchPng-24 165 ns/op 221 ns/op 1176 ns/op
|
||||
```
|
||||
|
||||
## Contributing
|
||||
See [CONTRIBUTING.md](CONTRIBUTING.md).
|
||||
@ -0,0 +1,309 @@
|
||||
package charset
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/xml"
|
||||
"strings"
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
const (
|
||||
F = 0 /* character never appears in text */
|
||||
T = 1 /* character appears in plain ASCII text */
|
||||
I = 2 /* character appears in ISO-8859 text */
|
||||
X = 3 /* character appears in non-ISO extended ASCII (Mac, IBM PC) */
|
||||
)
|
||||
|
||||
var (
|
||||
boms = []struct {
|
||||
bom []byte
|
||||
enc string
|
||||
}{
|
||||
{[]byte{0xEF, 0xBB, 0xBF}, "utf-8"},
|
||||
{[]byte{0x00, 0x00, 0xFE, 0xFF}, "utf-32be"},
|
||||
{[]byte{0xFF, 0xFE, 0x00, 0x00}, "utf-32le"},
|
||||
{[]byte{0xFE, 0xFF}, "utf-16be"},
|
||||
{[]byte{0xFF, 0xFE}, "utf-16le"},
|
||||
}
|
||||
|
||||
// https://github.com/file/file/blob/fa93fb9f7d21935f1c7644c47d2975d31f12b812/src/encoding.c#L241
|
||||
textChars = [256]byte{
|
||||
/* BEL BS HT LF VT FF CR */
|
||||
F, F, F, F, F, F, F, T, T, T, T, T, T, T, F, F, /* 0x0X */
|
||||
/* ESC */
|
||||
F, F, F, F, F, F, F, F, F, F, F, T, F, F, F, F, /* 0x1X */
|
||||
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, /* 0x2X */
|
||||
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, /* 0x3X */
|
||||
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, /* 0x4X */
|
||||
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, /* 0x5X */
|
||||
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, /* 0x6X */
|
||||
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, F, /* 0x7X */
|
||||
/* NEL */
|
||||
X, X, X, X, X, T, X, X, X, X, X, X, X, X, X, X, /* 0x8X */
|
||||
X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, /* 0x9X */
|
||||
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, /* 0xaX */
|
||||
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, /* 0xbX */
|
||||
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, /* 0xcX */
|
||||
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, /* 0xdX */
|
||||
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, /* 0xeX */
|
||||
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, /* 0xfX */
|
||||
}
|
||||
)
|
||||
|
||||
// FromBOM returns the charset declared in the BOM of content.
|
||||
func FromBOM(content []byte) string {
|
||||
for _, b := range boms {
|
||||
if bytes.HasPrefix(content, b.bom) {
|
||||
return b.enc
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// FromPlain returns the charset of a plain text. It relies on BOM presence
|
||||
// and it falls back on checking each byte in content.
|
||||
func FromPlain(content []byte) string {
|
||||
if len(content) == 0 {
|
||||
return ""
|
||||
}
|
||||
if cset := FromBOM(content); cset != "" {
|
||||
return cset
|
||||
}
|
||||
origContent := content
|
||||
// Try to detect UTF-8.
|
||||
// First eliminate any partial rune at the end.
|
||||
for i := len(content) - 1; i >= 0 && i > len(content)-4; i-- {
|
||||
b := content[i]
|
||||
if b < 0x80 {
|
||||
break
|
||||
}
|
||||
if utf8.RuneStart(b) {
|
||||
content = content[:i]
|
||||
break
|
||||
}
|
||||
}
|
||||
hasHighBit := false
|
||||
for _, c := range content {
|
||||
if c >= 0x80 {
|
||||
hasHighBit = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if hasHighBit && utf8.Valid(content) {
|
||||
return "utf-8"
|
||||
}
|
||||
|
||||
// ASCII is a subset of UTF8. Follow W3C recommendation and replace with UTF8.
|
||||
if ascii(origContent) {
|
||||
return "utf-8"
|
||||
}
|
||||
|
||||
return latin(origContent)
|
||||
}
|
||||
|
||||
func latin(content []byte) string {
|
||||
hasControlBytes := false
|
||||
for _, b := range content {
|
||||
t := textChars[b]
|
||||
if t != T && t != I {
|
||||
return ""
|
||||
}
|
||||
if b >= 0x80 && b <= 0x9F {
|
||||
hasControlBytes = true
|
||||
}
|
||||
}
|
||||
// Code range 0x80 to 0x9F is reserved for control characters in ISO-8859-1
|
||||
// (so-called C1 Controls). Windows 1252, however, has printable punctuation
|
||||
// characters in this range.
|
||||
if hasControlBytes {
|
||||
return "windows-1252"
|
||||
}
|
||||
return "iso-8859-1"
|
||||
}
|
||||
|
||||
func ascii(content []byte) bool {
|
||||
for _, b := range content {
|
||||
if textChars[b] != T {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// FromXML returns the charset of an XML document. It relies on the XML
|
||||
// header <?xml version="1.0" encoding="UTF-8"?> and falls back on the plain
|
||||
// text content.
|
||||
func FromXML(content []byte) string {
|
||||
if cset := fromXML(content); cset != "" {
|
||||
return cset
|
||||
}
|
||||
return FromPlain(content)
|
||||
}
|
||||
func fromXML(content []byte) string {
|
||||
content = trimLWS(content)
|
||||
dec := xml.NewDecoder(bytes.NewReader(content))
|
||||
rawT, err := dec.RawToken()
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
|
||||
t, ok := rawT.(xml.ProcInst)
|
||||
if !ok {
|
||||
return ""
|
||||
}
|
||||
|
||||
return strings.ToLower(xmlEncoding(string(t.Inst)))
|
||||
}
|
||||
|
||||
// FromHTML returns the charset of an HTML document. It first looks if a BOM is
|
||||
// present and if so uses it to determine the charset. If no BOM is present,
|
||||
// it relies on the meta tag <meta charset="UTF-8"> and falls back on the
|
||||
// plain text content.
|
||||
func FromHTML(content []byte) string {
|
||||
if cset := FromBOM(content); cset != "" {
|
||||
return cset
|
||||
}
|
||||
if cset := fromHTML(content); cset != "" {
|
||||
return cset
|
||||
}
|
||||
return FromPlain(content)
|
||||
}
|
||||
|
||||
func fromHTML(content []byte) string {
|
||||
z := html.NewTokenizer(bytes.NewReader(content))
|
||||
for {
|
||||
switch z.Next() {
|
||||
case html.ErrorToken:
|
||||
return ""
|
||||
|
||||
case html.StartTagToken, html.SelfClosingTagToken:
|
||||
tagName, hasAttr := z.TagName()
|
||||
if !bytes.Equal(tagName, []byte("meta")) {
|
||||
continue
|
||||
}
|
||||
attrList := make(map[string]bool)
|
||||
gotPragma := false
|
||||
|
||||
const (
|
||||
dontKnow = iota
|
||||
doNeedPragma
|
||||
doNotNeedPragma
|
||||
)
|
||||
needPragma := dontKnow
|
||||
|
||||
name := ""
|
||||
for hasAttr {
|
||||
var key, val []byte
|
||||
key, val, hasAttr = z.TagAttr()
|
||||
ks := string(key)
|
||||
if attrList[ks] {
|
||||
continue
|
||||
}
|
||||
attrList[ks] = true
|
||||
for i, c := range val {
|
||||
if 'A' <= c && c <= 'Z' {
|
||||
val[i] = c + 0x20
|
||||
}
|
||||
}
|
||||
|
||||
switch ks {
|
||||
case "http-equiv":
|
||||
if bytes.Equal(val, []byte("content-type")) {
|
||||
gotPragma = true
|
||||
}
|
||||
|
||||
case "content":
|
||||
name = fromMetaElement(string(val))
|
||||
if name != "" {
|
||||
needPragma = doNeedPragma
|
||||
}
|
||||
|
||||
case "charset":
|
||||
name = string(val)
|
||||
needPragma = doNotNeedPragma
|
||||
}
|
||||
}
|
||||
|
||||
if needPragma == dontKnow || needPragma == doNeedPragma && !gotPragma {
|
||||
continue
|
||||
}
|
||||
|
||||
if strings.HasPrefix(name, "utf-16") {
|
||||
name = "utf-8"
|
||||
}
|
||||
|
||||
return name
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func fromMetaElement(s string) string {
|
||||
for s != "" {
|
||||
csLoc := strings.Index(s, "charset")
|
||||
if csLoc == -1 {
|
||||
return ""
|
||||
}
|
||||
s = s[csLoc+len("charset"):]
|
||||
s = strings.TrimLeft(s, " \t\n\f\r")
|
||||
if !strings.HasPrefix(s, "=") {
|
||||
continue
|
||||
}
|
||||
s = s[1:]
|
||||
s = strings.TrimLeft(s, " \t\n\f\r")
|
||||
if s == "" {
|
||||
return ""
|
||||
}
|
||||
if q := s[0]; q == '"' || q == '\'' {
|
||||
s = s[1:]
|
||||
closeQuote := strings.IndexRune(s, rune(q))
|
||||
if closeQuote == -1 {
|
||||
return ""
|
||||
}
|
||||
return s[:closeQuote]
|
||||
}
|
||||
|
||||
end := strings.IndexAny(s, "; \t\n\f\r")
|
||||
if end == -1 {
|
||||
end = len(s)
|
||||
}
|
||||
return s[:end]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func xmlEncoding(s string) string {
|
||||
param := "encoding="
|
||||
idx := strings.Index(s, param)
|
||||
if idx == -1 {
|
||||
return ""
|
||||
}
|
||||
v := s[idx+len(param):]
|
||||
if v == "" {
|
||||
return ""
|
||||
}
|
||||
if v[0] != '\'' && v[0] != '"' {
|
||||
return ""
|
||||
}
|
||||
idx = strings.IndexRune(v[1:], rune(v[0]))
|
||||
if idx == -1 {
|
||||
return ""
|
||||
}
|
||||
return v[1 : idx+1]
|
||||
}
|
||||
|
||||
// trimLWS trims whitespace from beginning of the input.
|
||||
// TODO: find a way to call trimLWS once per detection instead of once in each
|
||||
// detector which needs the trimmed input.
|
||||
func trimLWS(in []byte) []byte {
|
||||
firstNonWS := 0
|
||||
for ; firstNonWS < len(in) && isWS(in[firstNonWS]); firstNonWS++ {
|
||||
}
|
||||
|
||||
return in[firstNonWS:]
|
||||
}
|
||||
|
||||
func isWS(b byte) bool {
|
||||
return b == '\t' || b == '\n' || b == '\x0c' || b == '\r' || b == ' '
|
||||
}
|
||||
@ -0,0 +1,544 @@
|
||||
// Copyright (c) 2009 The Go Authors. All rights reserved.
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without
|
||||
// modification, are permitted provided that the following conditions are
|
||||
// met:
|
||||
//
|
||||
// * Redistributions of source code must retain the above copyright
|
||||
// notice, this list of conditions and the following disclaimer.
|
||||
// * Redistributions in binary form must reproduce the above
|
||||
// copyright notice, this list of conditions and the following disclaimer
|
||||
// in the documentation and/or other materials provided with the
|
||||
// distribution.
|
||||
// * Neither the name of Google Inc. nor the names of its
|
||||
// contributors may be used to endorse or promote products derived from
|
||||
// this software without specific prior written permission.
|
||||
//
|
||||
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
// Package json provides a JSON value parser state machine.
|
||||
// This package is almost entirely copied from the Go stdlib.
|
||||
// Changes made to it permit users of the package to tell
|
||||
// if some slice of bytes is a valid beginning of a json string.
|
||||
package json
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
)
|
||||
|
||||
type (
|
||||
scanStatus int
|
||||
)
|
||||
|
||||
const (
|
||||
parseObjectKey = iota // parsing object key (before colon)
|
||||
parseObjectValue // parsing object value (after colon)
|
||||
parseArrayValue // parsing array value
|
||||
|
||||
scanContinue scanStatus = iota // uninteresting byte
|
||||
scanBeginLiteral // end implied by next result != scanContinue
|
||||
scanBeginObject // begin object
|
||||
scanObjectKey // just finished object key (string)
|
||||
scanObjectValue // just finished non-last object value
|
||||
scanEndObject // end object (implies scanObjectValue if possible)
|
||||
scanBeginArray // begin array
|
||||
scanArrayValue // just finished array value
|
||||
scanEndArray // end array (implies scanArrayValue if possible)
|
||||
scanSkipSpace // space byte; can skip; known to be last "continue" result
|
||||
scanEnd // top-level value ended *before* this byte; known to be first "stop" result
|
||||
scanError // hit an error, scanner.err.
|
||||
|
||||
// This limits the max nesting depth to prevent stack overflow.
|
||||
// This is permitted by https://tools.ietf.org/html/rfc7159#section-9
|
||||
maxNestingDepth = 10000
|
||||
)
|
||||
|
||||
type (
|
||||
scanner struct {
|
||||
step func(*scanner, byte) scanStatus
|
||||
parseState []int
|
||||
endTop bool
|
||||
err error
|
||||
index int
|
||||
}
|
||||
)
|
||||
|
||||
// Scan returns the number of bytes scanned and if there was any error
|
||||
// in trying to reach the end of data.
|
||||
func Scan(data []byte) (int, error) {
|
||||
s := &scanner{}
|
||||
_ = checkValid(data, s)
|
||||
return s.index, s.err
|
||||
}
|
||||
|
||||
// checkValid verifies that data is valid JSON-encoded data.
|
||||
// scan is passed in for use by checkValid to avoid an allocation.
|
||||
func checkValid(data []byte, scan *scanner) error {
|
||||
scan.reset()
|
||||
for _, c := range data {
|
||||
scan.index++
|
||||
if scan.step(scan, c) == scanError {
|
||||
return scan.err
|
||||
}
|
||||
}
|
||||
if scan.eof() == scanError {
|
||||
return scan.err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func isSpace(c byte) bool {
|
||||
return c == ' ' || c == '\t' || c == '\r' || c == '\n'
|
||||
}
|
||||
|
||||
func (s *scanner) reset() {
|
||||
s.step = stateBeginValue
|
||||
s.parseState = s.parseState[0:0]
|
||||
s.err = nil
|
||||
}
|
||||
|
||||
// eof tells the scanner that the end of input has been reached.
|
||||
// It returns a scan status just as s.step does.
|
||||
func (s *scanner) eof() scanStatus {
|
||||
if s.err != nil {
|
||||
return scanError
|
||||
}
|
||||
if s.endTop {
|
||||
return scanEnd
|
||||
}
|
||||
s.step(s, ' ')
|
||||
if s.endTop {
|
||||
return scanEnd
|
||||
}
|
||||
if s.err == nil {
|
||||
s.err = fmt.Errorf("unexpected end of JSON input")
|
||||
}
|
||||
return scanError
|
||||
}
|
||||
|
||||
// pushParseState pushes a new parse state p onto the parse stack.
|
||||
// an error state is returned if maxNestingDepth was exceeded, otherwise successState is returned.
|
||||
func (s *scanner) pushParseState(c byte, newParseState int, successState scanStatus) scanStatus {
|
||||
s.parseState = append(s.parseState, newParseState)
|
||||
if len(s.parseState) <= maxNestingDepth {
|
||||
return successState
|
||||
}
|
||||
return s.error(c, "exceeded max depth")
|
||||
}
|
||||
|
||||
// popParseState pops a parse state (already obtained) off the stack
|
||||
// and updates s.step accordingly.
|
||||
func (s *scanner) popParseState() {
|
||||
n := len(s.parseState) - 1
|
||||
s.parseState = s.parseState[0:n]
|
||||
if n == 0 {
|
||||
s.step = stateEndTop
|
||||
s.endTop = true
|
||||
} else {
|
||||
s.step = stateEndValue
|
||||
}
|
||||
}
|
||||
|
||||
// stateBeginValueOrEmpty is the state after reading `[`.
|
||||
func stateBeginValueOrEmpty(s *scanner, c byte) scanStatus {
|
||||
if c <= ' ' && isSpace(c) {
|
||||
return scanSkipSpace
|
||||
}
|
||||
if c == ']' {
|
||||
return stateEndValue(s, c)
|
||||
}
|
||||
return stateBeginValue(s, c)
|
||||
}
|
||||
|
||||
// stateBeginValue is the state at the beginning of the input.
|
||||
func stateBeginValue(s *scanner, c byte) scanStatus {
|
||||
if c <= ' ' && isSpace(c) {
|
||||
return scanSkipSpace
|
||||
}
|
||||
switch c {
|
||||
case '{':
|
||||
s.step = stateBeginStringOrEmpty
|
||||
return s.pushParseState(c, parseObjectKey, scanBeginObject)
|
||||
case '[':
|
||||
s.step = stateBeginValueOrEmpty
|
||||
return s.pushParseState(c, parseArrayValue, scanBeginArray)
|
||||
case '"':
|
||||
s.step = stateInString
|
||||
return scanBeginLiteral
|
||||
case '-':
|
||||
s.step = stateNeg
|
||||
return scanBeginLiteral
|
||||
case '0': // beginning of 0.123
|
||||
s.step = state0
|
||||
return scanBeginLiteral
|
||||
case 't': // beginning of true
|
||||
s.step = stateT
|
||||
return scanBeginLiteral
|
||||
case 'f': // beginning of false
|
||||
s.step = stateF
|
||||
return scanBeginLiteral
|
||||
case 'n': // beginning of null
|
||||
s.step = stateN
|
||||
return scanBeginLiteral
|
||||
}
|
||||
if '1' <= c && c <= '9' { // beginning of 1234.5
|
||||
s.step = state1
|
||||
return scanBeginLiteral
|
||||
}
|
||||
return s.error(c, "looking for beginning of value")
|
||||
}
|
||||
|
||||
// stateBeginStringOrEmpty is the state after reading `{`.
|
||||
func stateBeginStringOrEmpty(s *scanner, c byte) scanStatus {
|
||||
if c <= ' ' && isSpace(c) {
|
||||
return scanSkipSpace
|
||||
}
|
||||
if c == '}' {
|
||||
n := len(s.parseState)
|
||||
s.parseState[n-1] = parseObjectValue
|
||||
return stateEndValue(s, c)
|
||||
}
|
||||
return stateBeginString(s, c)
|
||||
}
|
||||
|
||||
// stateBeginString is the state after reading `{"key": value,`.
|
||||
func stateBeginString(s *scanner, c byte) scanStatus {
|
||||
if c <= ' ' && isSpace(c) {
|
||||
return scanSkipSpace
|
||||
}
|
||||
if c == '"' {
|
||||
s.step = stateInString
|
||||
return scanBeginLiteral
|
||||
}
|
||||
return s.error(c, "looking for beginning of object key string")
|
||||
}
|
||||
|
||||
// stateEndValue is the state after completing a value,
|
||||
// such as after reading `{}` or `true` or `["x"`.
|
||||
func stateEndValue(s *scanner, c byte) scanStatus {
|
||||
n := len(s.parseState)
|
||||
if n == 0 {
|
||||
// Completed top-level before the current byte.
|
||||
s.step = stateEndTop
|
||||
s.endTop = true
|
||||
return stateEndTop(s, c)
|
||||
}
|
||||
if c <= ' ' && isSpace(c) {
|
||||
s.step = stateEndValue
|
||||
return scanSkipSpace
|
||||
}
|
||||
ps := s.parseState[n-1]
|
||||
switch ps {
|
||||
case parseObjectKey:
|
||||
if c == ':' {
|
||||
s.parseState[n-1] = parseObjectValue
|
||||
s.step = stateBeginValue
|
||||
return scanObjectKey
|
||||
}
|
||||
return s.error(c, "after object key")
|
||||
case parseObjectValue:
|
||||
if c == ',' {
|
||||
s.parseState[n-1] = parseObjectKey
|
||||
s.step = stateBeginString
|
||||
return scanObjectValue
|
||||
}
|
||||
if c == '}' {
|
||||
s.popParseState()
|
||||
return scanEndObject
|
||||
}
|
||||
return s.error(c, "after object key:value pair")
|
||||
case parseArrayValue:
|
||||
if c == ',' {
|
||||
s.step = stateBeginValue
|
||||
return scanArrayValue
|
||||
}
|
||||
if c == ']' {
|
||||
s.popParseState()
|
||||
return scanEndArray
|
||||
}
|
||||
return s.error(c, "after array element")
|
||||
}
|
||||
return s.error(c, "")
|
||||
}
|
||||
|
||||
// stateEndTop is the state after finishing the top-level value,
|
||||
// such as after reading `{}` or `[1,2,3]`.
|
||||
// Only space characters should be seen now.
|
||||
func stateEndTop(s *scanner, c byte) scanStatus {
|
||||
if c != ' ' && c != '\t' && c != '\r' && c != '\n' {
|
||||
// Complain about non-space byte on next call.
|
||||
s.error(c, "after top-level value")
|
||||
}
|
||||
return scanEnd
|
||||
}
|
||||
|
||||
// stateInString is the state after reading `"`.
|
||||
func stateInString(s *scanner, c byte) scanStatus {
|
||||
if c == '"' {
|
||||
s.step = stateEndValue
|
||||
return scanContinue
|
||||
}
|
||||
if c == '\\' {
|
||||
s.step = stateInStringEsc
|
||||
return scanContinue
|
||||
}
|
||||
if c < 0x20 {
|
||||
return s.error(c, "in string literal")
|
||||
}
|
||||
return scanContinue
|
||||
}
|
||||
|
||||
// stateInStringEsc is the state after reading `"\` during a quoted string.
|
||||
func stateInStringEsc(s *scanner, c byte) scanStatus {
|
||||
switch c {
|
||||
case 'b', 'f', 'n', 'r', 't', '\\', '/', '"':
|
||||
s.step = stateInString
|
||||
return scanContinue
|
||||
case 'u':
|
||||
s.step = stateInStringEscU
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in string escape code")
|
||||
}
|
||||
|
||||
// stateInStringEscU is the state after reading `"\u` during a quoted string.
|
||||
func stateInStringEscU(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
|
||||
s.step = stateInStringEscU1
|
||||
return scanContinue
|
||||
}
|
||||
// numbers
|
||||
return s.error(c, "in \\u hexadecimal character escape")
|
||||
}
|
||||
|
||||
// stateInStringEscU1 is the state after reading `"\u1` during a quoted string.
|
||||
func stateInStringEscU1(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
|
||||
s.step = stateInStringEscU12
|
||||
return scanContinue
|
||||
}
|
||||
// numbers
|
||||
return s.error(c, "in \\u hexadecimal character escape")
|
||||
}
|
||||
|
||||
// stateInStringEscU12 is the state after reading `"\u12` during a quoted string.
|
||||
func stateInStringEscU12(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
|
||||
s.step = stateInStringEscU123
|
||||
return scanContinue
|
||||
}
|
||||
// numbers
|
||||
return s.error(c, "in \\u hexadecimal character escape")
|
||||
}
|
||||
|
||||
// stateInStringEscU123 is the state after reading `"\u123` during a quoted string.
|
||||
func stateInStringEscU123(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
|
||||
s.step = stateInString
|
||||
return scanContinue
|
||||
}
|
||||
// numbers
|
||||
return s.error(c, "in \\u hexadecimal character escape")
|
||||
}
|
||||
|
||||
// stateNeg is the state after reading `-` during a number.
|
||||
func stateNeg(s *scanner, c byte) scanStatus {
|
||||
if c == '0' {
|
||||
s.step = state0
|
||||
return scanContinue
|
||||
}
|
||||
if '1' <= c && c <= '9' {
|
||||
s.step = state1
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in numeric literal")
|
||||
}
|
||||
|
||||
// state1 is the state after reading a non-zero integer during a number,
|
||||
// such as after reading `1` or `100` but not `0`.
|
||||
func state1(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' {
|
||||
s.step = state1
|
||||
return scanContinue
|
||||
}
|
||||
return state0(s, c)
|
||||
}
|
||||
|
||||
// state0 is the state after reading `0` during a number.
|
||||
func state0(s *scanner, c byte) scanStatus {
|
||||
if c == '.' {
|
||||
s.step = stateDot
|
||||
return scanContinue
|
||||
}
|
||||
if c == 'e' || c == 'E' {
|
||||
s.step = stateE
|
||||
return scanContinue
|
||||
}
|
||||
return stateEndValue(s, c)
|
||||
}
|
||||
|
||||
// stateDot is the state after reading the integer and decimal point in a number,
|
||||
// such as after reading `1.`.
|
||||
func stateDot(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' {
|
||||
s.step = stateDot0
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "after decimal point in numeric literal")
|
||||
}
|
||||
|
||||
// stateDot0 is the state after reading the integer, decimal point, and subsequent
|
||||
// digits of a number, such as after reading `3.14`.
|
||||
func stateDot0(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' {
|
||||
return scanContinue
|
||||
}
|
||||
if c == 'e' || c == 'E' {
|
||||
s.step = stateE
|
||||
return scanContinue
|
||||
}
|
||||
return stateEndValue(s, c)
|
||||
}
|
||||
|
||||
// stateE is the state after reading the mantissa and e in a number,
|
||||
// such as after reading `314e` or `0.314e`.
|
||||
func stateE(s *scanner, c byte) scanStatus {
|
||||
if c == '+' || c == '-' {
|
||||
s.step = stateESign
|
||||
return scanContinue
|
||||
}
|
||||
return stateESign(s, c)
|
||||
}
|
||||
|
||||
// stateESign is the state after reading the mantissa, e, and sign in a number,
|
||||
// such as after reading `314e-` or `0.314e+`.
|
||||
func stateESign(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' {
|
||||
s.step = stateE0
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in exponent of numeric literal")
|
||||
}
|
||||
|
||||
// stateE0 is the state after reading the mantissa, e, optional sign,
|
||||
// and at least one digit of the exponent in a number,
|
||||
// such as after reading `314e-2` or `0.314e+1` or `3.14e0`.
|
||||
func stateE0(s *scanner, c byte) scanStatus {
|
||||
if '0' <= c && c <= '9' {
|
||||
return scanContinue
|
||||
}
|
||||
return stateEndValue(s, c)
|
||||
}
|
||||
|
||||
// stateT is the state after reading `t`.
|
||||
func stateT(s *scanner, c byte) scanStatus {
|
||||
if c == 'r' {
|
||||
s.step = stateTr
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal true (expecting 'r')")
|
||||
}
|
||||
|
||||
// stateTr is the state after reading `tr`.
|
||||
func stateTr(s *scanner, c byte) scanStatus {
|
||||
if c == 'u' {
|
||||
s.step = stateTru
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal true (expecting 'u')")
|
||||
}
|
||||
|
||||
// stateTru is the state after reading `tru`.
|
||||
func stateTru(s *scanner, c byte) scanStatus {
|
||||
if c == 'e' {
|
||||
s.step = stateEndValue
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal true (expecting 'e')")
|
||||
}
|
||||
|
||||
// stateF is the state after reading `f`.
|
||||
func stateF(s *scanner, c byte) scanStatus {
|
||||
if c == 'a' {
|
||||
s.step = stateFa
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal false (expecting 'a')")
|
||||
}
|
||||
|
||||
// stateFa is the state after reading `fa`.
|
||||
func stateFa(s *scanner, c byte) scanStatus {
|
||||
if c == 'l' {
|
||||
s.step = stateFal
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal false (expecting 'l')")
|
||||
}
|
||||
|
||||
// stateFal is the state after reading `fal`.
|
||||
func stateFal(s *scanner, c byte) scanStatus {
|
||||
if c == 's' {
|
||||
s.step = stateFals
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal false (expecting 's')")
|
||||
}
|
||||
|
||||
// stateFals is the state after reading `fals`.
|
||||
func stateFals(s *scanner, c byte) scanStatus {
|
||||
if c == 'e' {
|
||||
s.step = stateEndValue
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal false (expecting 'e')")
|
||||
}
|
||||
|
||||
// stateN is the state after reading `n`.
|
||||
func stateN(s *scanner, c byte) scanStatus {
|
||||
if c == 'u' {
|
||||
s.step = stateNu
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal null (expecting 'u')")
|
||||
}
|
||||
|
||||
// stateNu is the state after reading `nu`.
|
||||
func stateNu(s *scanner, c byte) scanStatus {
|
||||
if c == 'l' {
|
||||
s.step = stateNul
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal null (expecting 'l')")
|
||||
}
|
||||
|
||||
// stateNul is the state after reading `nul`.
|
||||
func stateNul(s *scanner, c byte) scanStatus {
|
||||
if c == 'l' {
|
||||
s.step = stateEndValue
|
||||
return scanContinue
|
||||
}
|
||||
return s.error(c, "in literal null (expecting 'l')")
|
||||
}
|
||||
|
||||
// stateError is the state after reaching a syntax error,
|
||||
// such as after reading `[1}` or `5.1.2`.
|
||||
func stateError(s *scanner, c byte) scanStatus {
|
||||
return scanError
|
||||
}
|
||||
|
||||
// error records an error and switches to the error state.
|
||||
func (s *scanner) error(c byte, context string) scanStatus {
|
||||
s.step = stateError
|
||||
s.err = fmt.Errorf("invalid character <<%c>> %s", c, context)
|
||||
return scanError
|
||||
}
|
||||
@ -0,0 +1,124 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
)
|
||||
|
||||
var (
|
||||
// SevenZ matches a 7z archive.
|
||||
SevenZ = prefix([]byte{0x37, 0x7A, 0xBC, 0xAF, 0x27, 0x1C})
|
||||
// Gzip matches gzip files based on http://www.zlib.org/rfc-gzip.html#header-trailer.
|
||||
Gzip = prefix([]byte{0x1f, 0x8b})
|
||||
// Fits matches an Flexible Image Transport System file.
|
||||
Fits = prefix([]byte{
|
||||
0x53, 0x49, 0x4D, 0x50, 0x4C, 0x45, 0x20, 0x20, 0x3D, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x54,
|
||||
})
|
||||
// Xar matches an eXtensible ARchive format file.
|
||||
Xar = prefix([]byte{0x78, 0x61, 0x72, 0x21})
|
||||
// Bz2 matches a bzip2 file.
|
||||
Bz2 = prefix([]byte{0x42, 0x5A, 0x68})
|
||||
// Ar matches an ar (Unix) archive file.
|
||||
Ar = prefix([]byte{0x21, 0x3C, 0x61, 0x72, 0x63, 0x68, 0x3E})
|
||||
// Deb matches a Debian package file.
|
||||
Deb = offset([]byte{
|
||||
0x64, 0x65, 0x62, 0x69, 0x61, 0x6E, 0x2D,
|
||||
0x62, 0x69, 0x6E, 0x61, 0x72, 0x79,
|
||||
}, 8)
|
||||
// Warc matches a Web ARChive file.
|
||||
Warc = prefix([]byte("WARC/1.0"), []byte("WARC/1.1"))
|
||||
// Cab matches a Microsoft Cabinet archive file.
|
||||
Cab = prefix([]byte("MSCF\x00\x00\x00\x00"))
|
||||
// Xz matches an xz compressed stream based on https://tukaani.org/xz/xz-file-format.txt.
|
||||
Xz = prefix([]byte{0xFD, 0x37, 0x7A, 0x58, 0x5A, 0x00})
|
||||
// Lzip matches an Lzip compressed file.
|
||||
Lzip = prefix([]byte{0x4c, 0x5a, 0x49, 0x50})
|
||||
// RPM matches an RPM or Delta RPM package file.
|
||||
RPM = prefix([]byte{0xed, 0xab, 0xee, 0xdb}, []byte("drpm"))
|
||||
// Cpio matches a cpio archive file.
|
||||
Cpio = prefix([]byte("070707"), []byte("070701"), []byte("070702"))
|
||||
// RAR matches a RAR archive file.
|
||||
RAR = prefix([]byte("Rar!\x1A\x07\x00"), []byte("Rar!\x1A\x07\x01\x00"))
|
||||
)
|
||||
|
||||
// InstallShieldCab matches an InstallShield Cabinet archive file.
|
||||
func InstallShieldCab(raw []byte, _ uint32) bool {
|
||||
return len(raw) > 7 &&
|
||||
bytes.Equal(raw[0:4], []byte("ISc(")) &&
|
||||
raw[6] == 0 &&
|
||||
(raw[7] == 1 || raw[7] == 2 || raw[7] == 4)
|
||||
}
|
||||
|
||||
// Zstd matches a Zstandard archive file.
|
||||
func Zstd(raw []byte, limit uint32) bool {
|
||||
return len(raw) >= 4 &&
|
||||
(0x22 <= raw[0] && raw[0] <= 0x28 || raw[0] == 0x1E) && // Different Zstandard versions.
|
||||
bytes.HasPrefix(raw[1:], []byte{0xB5, 0x2F, 0xFD})
|
||||
}
|
||||
|
||||
// CRX matches a Chrome extension file: a zip archive prepended by a package header.
|
||||
func CRX(raw []byte, limit uint32) bool {
|
||||
const minHeaderLen = 16
|
||||
if len(raw) < minHeaderLen || !bytes.HasPrefix(raw, []byte("Cr24")) {
|
||||
return false
|
||||
}
|
||||
pubkeyLen := binary.LittleEndian.Uint32(raw[8:12])
|
||||
sigLen := binary.LittleEndian.Uint32(raw[12:16])
|
||||
zipOffset := minHeaderLen + pubkeyLen + sigLen
|
||||
if uint32(len(raw)) < zipOffset {
|
||||
return false
|
||||
}
|
||||
return Zip(raw[zipOffset:], limit)
|
||||
}
|
||||
|
||||
// Tar matches a (t)ape (ar)chive file.
|
||||
func Tar(raw []byte, _ uint32) bool {
|
||||
// The "magic" header field for files in in UStar (POSIX IEEE P1003.1) archives
|
||||
// has the prefix "ustar". The values of the remaining bytes in this field vary
|
||||
// by archiver implementation.
|
||||
if len(raw) >= 512 && bytes.HasPrefix(raw[257:], []byte{0x75, 0x73, 0x74, 0x61, 0x72}) {
|
||||
return true
|
||||
}
|
||||
|
||||
if len(raw) < 256 {
|
||||
return false
|
||||
}
|
||||
|
||||
// The older v7 format has no "magic" field, and therefore must be identified
|
||||
// with heuristics based on legal ranges of values for other header fields:
|
||||
// https://www.nationalarchives.gov.uk/PRONOM/Format/proFormatSearch.aspx?status=detailReport&id=385&strPageToDisplay=signatures
|
||||
rules := []struct {
|
||||
min, max uint8
|
||||
i int
|
||||
}{
|
||||
{0x21, 0xEF, 0},
|
||||
{0x30, 0x37, 105},
|
||||
{0x20, 0x37, 106},
|
||||
{0x00, 0x00, 107},
|
||||
{0x30, 0x37, 113},
|
||||
{0x20, 0x37, 114},
|
||||
{0x00, 0x00, 115},
|
||||
{0x30, 0x37, 121},
|
||||
{0x20, 0x37, 122},
|
||||
{0x00, 0x00, 123},
|
||||
{0x30, 0x37, 134},
|
||||
{0x30, 0x37, 146},
|
||||
{0x30, 0x37, 153},
|
||||
{0x00, 0x37, 154},
|
||||
}
|
||||
for _, r := range rules {
|
||||
if raw[r.i] < r.min || raw[r.i] > r.max {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
for _, i := range []uint8{135, 147, 155} {
|
||||
if raw[i] != 0x00 && raw[i] != 0x20 {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
return true
|
||||
}
|
||||
@ -0,0 +1,76 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
)
|
||||
|
||||
var (
|
||||
// Flac matches a Free Lossless Audio Codec file.
|
||||
Flac = prefix([]byte("\x66\x4C\x61\x43\x00\x00\x00\x22"))
|
||||
// Midi matches a Musical Instrument Digital Interface file.
|
||||
Midi = prefix([]byte("\x4D\x54\x68\x64"))
|
||||
// Ape matches a Monkey's Audio file.
|
||||
Ape = prefix([]byte("\x4D\x41\x43\x20\x96\x0F\x00\x00\x34\x00\x00\x00\x18\x00\x00\x00\x90\xE3"))
|
||||
// MusePack matches a Musepack file.
|
||||
MusePack = prefix([]byte("MPCK"))
|
||||
// Au matches a Sun Microsystems au file.
|
||||
Au = prefix([]byte("\x2E\x73\x6E\x64"))
|
||||
// Amr matches an Adaptive Multi-Rate file.
|
||||
Amr = prefix([]byte("\x23\x21\x41\x4D\x52"))
|
||||
// Voc matches a Creative Voice file.
|
||||
Voc = prefix([]byte("Creative Voice File"))
|
||||
// M3u matches a Playlist file.
|
||||
M3u = prefix([]byte("#EXTM3U"))
|
||||
// AAC matches an Advanced Audio Coding file.
|
||||
AAC = prefix([]byte{0xFF, 0xF1}, []byte{0xFF, 0xF9})
|
||||
)
|
||||
|
||||
// Mp3 matches an mp3 file.
|
||||
func Mp3(raw []byte, limit uint32) bool {
|
||||
if len(raw) < 3 {
|
||||
return false
|
||||
}
|
||||
|
||||
if bytes.HasPrefix(raw, []byte("ID3")) {
|
||||
// MP3s with an ID3v2 tag will start with "ID3"
|
||||
// ID3v1 tags, however appear at the end of the file.
|
||||
return true
|
||||
}
|
||||
|
||||
// Match MP3 files without tags
|
||||
switch binary.BigEndian.Uint16(raw[:2]) & 0xFFFE {
|
||||
case 0xFFFA:
|
||||
// MPEG ADTS, layer III, v1
|
||||
return true
|
||||
case 0xFFF2:
|
||||
// MPEG ADTS, layer III, v2
|
||||
return true
|
||||
case 0xFFE2:
|
||||
// MPEG ADTS, layer III, v2.5
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// Wav matches a Waveform Audio File Format file.
|
||||
func Wav(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 12 &&
|
||||
bytes.Equal(raw[:4], []byte("RIFF")) &&
|
||||
bytes.Equal(raw[8:12], []byte{0x57, 0x41, 0x56, 0x45})
|
||||
}
|
||||
|
||||
// Aiff matches Audio Interchange File Format file.
|
||||
func Aiff(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 12 &&
|
||||
bytes.Equal(raw[:4], []byte{0x46, 0x4F, 0x52, 0x4D}) &&
|
||||
bytes.Equal(raw[8:12], []byte{0x41, 0x49, 0x46, 0x46})
|
||||
}
|
||||
|
||||
// Qcp matches a Qualcomm Pure Voice file.
|
||||
func Qcp(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 12 &&
|
||||
bytes.Equal(raw[:4], []byte("RIFF")) &&
|
||||
bytes.Equal(raw[8:12], []byte("QLCM"))
|
||||
}
|
||||
@ -0,0 +1,196 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"debug/macho"
|
||||
"encoding/binary"
|
||||
)
|
||||
|
||||
var (
|
||||
// Lnk matches Microsoft lnk binary format.
|
||||
Lnk = prefix([]byte{0x4C, 0x00, 0x00, 0x00, 0x01, 0x14, 0x02, 0x00})
|
||||
// Wasm matches a web assembly File Format file.
|
||||
Wasm = prefix([]byte{0x00, 0x61, 0x73, 0x6D})
|
||||
// Exe matches a Windows/DOS executable file.
|
||||
Exe = prefix([]byte{0x4D, 0x5A})
|
||||
// Elf matches an Executable and Linkable Format file.
|
||||
Elf = prefix([]byte{0x7F, 0x45, 0x4C, 0x46})
|
||||
// Nes matches a Nintendo Entertainment system ROM file.
|
||||
Nes = prefix([]byte{0x4E, 0x45, 0x53, 0x1A})
|
||||
// SWF matches an Adobe Flash swf file.
|
||||
SWF = prefix([]byte("CWS"), []byte("FWS"), []byte("ZWS"))
|
||||
// Torrent has bencoded text in the beginning.
|
||||
Torrent = prefix([]byte("d8:announce"))
|
||||
)
|
||||
|
||||
// Java bytecode and Mach-O binaries share the same magic number.
|
||||
// More info here https://github.com/threatstack/libmagic/blob/master/magic/Magdir/cafebabe
|
||||
func classOrMachOFat(in []byte) bool {
|
||||
// There should be at least 8 bytes for both of them because the only way to
|
||||
// quickly distinguish them is by comparing byte at position 7
|
||||
if len(in) < 8 {
|
||||
return false
|
||||
}
|
||||
|
||||
return bytes.HasPrefix(in, []byte{0xCA, 0xFE, 0xBA, 0xBE})
|
||||
}
|
||||
|
||||
// Class matches a java class file.
|
||||
func Class(raw []byte, limit uint32) bool {
|
||||
return classOrMachOFat(raw) && raw[7] > 30
|
||||
}
|
||||
|
||||
// MachO matches Mach-O binaries format.
|
||||
func MachO(raw []byte, limit uint32) bool {
|
||||
if classOrMachOFat(raw) && raw[7] < 20 {
|
||||
return true
|
||||
}
|
||||
|
||||
if len(raw) < 4 {
|
||||
return false
|
||||
}
|
||||
|
||||
be := binary.BigEndian.Uint32(raw)
|
||||
le := binary.LittleEndian.Uint32(raw)
|
||||
|
||||
return be == macho.Magic32 ||
|
||||
le == macho.Magic32 ||
|
||||
be == macho.Magic64 ||
|
||||
le == macho.Magic64
|
||||
}
|
||||
|
||||
// Dbf matches a dBase file.
|
||||
// https://www.dbase.com/Knowledgebase/INT/db7_file_fmt.htm
|
||||
func Dbf(raw []byte, limit uint32) bool {
|
||||
if len(raw) < 68 {
|
||||
return false
|
||||
}
|
||||
|
||||
// 3rd and 4th bytes contain the last update month and day of month.
|
||||
if !(0 < raw[2] && raw[2] < 13 && 0 < raw[3] && raw[3] < 32) {
|
||||
return false
|
||||
}
|
||||
|
||||
// 12, 13, 30, 31 are reserved bytes and always filled with 0x00.
|
||||
if raw[12] != 0x00 || raw[13] != 0x00 || raw[30] != 0x00 || raw[31] != 0x00 {
|
||||
return false
|
||||
}
|
||||
// Production MDX flag;
|
||||
// 0x01 if a production .MDX file exists for this table;
|
||||
// 0x00 if no .MDX file exists.
|
||||
if raw[28] > 0x01 {
|
||||
return false
|
||||
}
|
||||
|
||||
// dbf type is dictated by the first byte.
|
||||
dbfTypes := []byte{
|
||||
0x02, 0x03, 0x04, 0x05, 0x30, 0x31, 0x32, 0x42, 0x62, 0x7B, 0x82,
|
||||
0x83, 0x87, 0x8A, 0x8B, 0x8E, 0xB3, 0xCB, 0xE5, 0xF5, 0xF4, 0xFB,
|
||||
}
|
||||
for _, b := range dbfTypes {
|
||||
if raw[0] == b {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// ElfObj matches an object file.
|
||||
func ElfObj(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 17 && ((raw[16] == 0x01 && raw[17] == 0x00) ||
|
||||
(raw[16] == 0x00 && raw[17] == 0x01))
|
||||
}
|
||||
|
||||
// ElfExe matches an executable file.
|
||||
func ElfExe(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 17 && ((raw[16] == 0x02 && raw[17] == 0x00) ||
|
||||
(raw[16] == 0x00 && raw[17] == 0x02))
|
||||
}
|
||||
|
||||
// ElfLib matches a shared library file.
|
||||
func ElfLib(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 17 && ((raw[16] == 0x03 && raw[17] == 0x00) ||
|
||||
(raw[16] == 0x00 && raw[17] == 0x03))
|
||||
}
|
||||
|
||||
// ElfDump matches a core dump file.
|
||||
func ElfDump(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 17 && ((raw[16] == 0x04 && raw[17] == 0x00) ||
|
||||
(raw[16] == 0x00 && raw[17] == 0x04))
|
||||
}
|
||||
|
||||
// Dcm matches a DICOM medical format file.
|
||||
func Dcm(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 131 &&
|
||||
bytes.Equal(raw[128:132], []byte{0x44, 0x49, 0x43, 0x4D})
|
||||
}
|
||||
|
||||
// Marc matches a MARC21 (MAchine-Readable Cataloging) file.
|
||||
func Marc(raw []byte, limit uint32) bool {
|
||||
// File is at least 24 bytes ("leader" field size).
|
||||
if len(raw) < 24 {
|
||||
return false
|
||||
}
|
||||
|
||||
// Fixed bytes at offset 20.
|
||||
if !bytes.Equal(raw[20:24], []byte("4500")) {
|
||||
return false
|
||||
}
|
||||
|
||||
// First 5 bytes are ASCII digits.
|
||||
for i := 0; i < 5; i++ {
|
||||
if raw[i] < '0' || raw[i] > '9' {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// Field terminator is present in first 2048 bytes.
|
||||
return bytes.Contains(raw[:min(2048, len(raw))], []byte{0x1E})
|
||||
}
|
||||
|
||||
// Glb matches a glTF model format file.
|
||||
// GLB is the binary file format representation of 3D models save in
|
||||
// the GL transmission Format (glTF).
|
||||
// see more: https://docs.fileformat.com/3d/glb/
|
||||
// https://www.iana.org/assignments/media-types/model/gltf-binary
|
||||
// GLB file format is based on little endian and its header structure
|
||||
// show below:
|
||||
//
|
||||
// <-- 12-byte header -->
|
||||
// | magic | version | length |
|
||||
// | (uint32) | (uint32) | (uint32) |
|
||||
// | \x67\x6C\x54\x46 | \x01\x00\x00\x00 | ... |
|
||||
// | g l T F | 1 | ... |
|
||||
var Glb = prefix([]byte("\x67\x6C\x54\x46\x02\x00\x00\x00"),
|
||||
[]byte("\x67\x6C\x54\x46\x01\x00\x00\x00"))
|
||||
|
||||
// TzIf matches a Time Zone Information Format (TZif) file.
|
||||
// See more: https://tools.ietf.org/id/draft-murchison-tzdist-tzif-00.html#rfc.section.3
|
||||
// Its header structure is shown below:
|
||||
// +---------------+---+
|
||||
// | magic (4) | <-+-- version (1)
|
||||
// +---------------+---+---------------------------------------+
|
||||
// | [unused - reserved for future use] (15) |
|
||||
// +---------------+---------------+---------------+-----------+
|
||||
// | isutccnt (4) | isstdcnt (4) | leapcnt (4) |
|
||||
// +---------------+---------------+---------------+
|
||||
// | timecnt (4) | typecnt (4) | charcnt (4) |
|
||||
func TzIf(raw []byte, limit uint32) bool {
|
||||
// File is at least 44 bytes (header size).
|
||||
if len(raw) < 44 {
|
||||
return false
|
||||
}
|
||||
|
||||
if !bytes.HasPrefix(raw, []byte("TZif")) {
|
||||
return false
|
||||
}
|
||||
|
||||
// Field "typecnt" MUST not be zero.
|
||||
if binary.BigEndian.Uint32(raw[36:40]) == 0 {
|
||||
return false
|
||||
}
|
||||
|
||||
// Version has to be NUL (0x00), '2' (0x32) or '3' (0x33).
|
||||
return raw[4] == 0x00 || raw[4] == 0x32 || raw[4] == 0x33
|
||||
}
|
||||
@ -0,0 +1,13 @@
|
||||
package magic
|
||||
|
||||
var (
|
||||
// Sqlite matches an SQLite database file.
|
||||
Sqlite = prefix([]byte{
|
||||
0x53, 0x51, 0x4c, 0x69, 0x74, 0x65, 0x20, 0x66,
|
||||
0x6f, 0x72, 0x6d, 0x61, 0x74, 0x20, 0x33, 0x00,
|
||||
})
|
||||
// MsAccessAce matches Microsoft Access dababase file.
|
||||
MsAccessAce = offset([]byte("Standard ACE DB"), 4)
|
||||
// MsAccessMdb matches legacy Microsoft Access database file (JET, 2003 and earlier).
|
||||
MsAccessMdb = offset([]byte("Standard Jet DB"), 4)
|
||||
)
|
||||
@ -0,0 +1,62 @@
|
||||
package magic
|
||||
|
||||
import "bytes"
|
||||
|
||||
var (
|
||||
// Pdf matches a Portable Document Format file.
|
||||
// https://github.com/file/file/blob/11010cc805546a3e35597e67e1129a481aed40e8/magic/Magdir/pdf
|
||||
Pdf = prefix(
|
||||
// usual pdf signature
|
||||
[]byte("%PDF-"),
|
||||
// new-line prefixed signature
|
||||
[]byte("\012%PDF-"),
|
||||
// UTF-8 BOM prefixed signature
|
||||
[]byte("\xef\xbb\xbf%PDF-"),
|
||||
)
|
||||
// Fdf matches a Forms Data Format file.
|
||||
Fdf = prefix([]byte("%FDF"))
|
||||
// Mobi matches a Mobi file.
|
||||
Mobi = offset([]byte("BOOKMOBI"), 60)
|
||||
// Lit matches a Microsoft Lit file.
|
||||
Lit = prefix([]byte("ITOLITLS"))
|
||||
)
|
||||
|
||||
// DjVu matches a DjVu file.
|
||||
func DjVu(raw []byte, limit uint32) bool {
|
||||
if len(raw) < 12 {
|
||||
return false
|
||||
}
|
||||
if !bytes.HasPrefix(raw, []byte{0x41, 0x54, 0x26, 0x54, 0x46, 0x4F, 0x52, 0x4D}) {
|
||||
return false
|
||||
}
|
||||
return bytes.HasPrefix(raw[12:], []byte("DJVM")) ||
|
||||
bytes.HasPrefix(raw[12:], []byte("DJVU")) ||
|
||||
bytes.HasPrefix(raw[12:], []byte("DJVI")) ||
|
||||
bytes.HasPrefix(raw[12:], []byte("THUM"))
|
||||
}
|
||||
|
||||
// P7s matches an .p7s signature File (PEM, Base64).
|
||||
func P7s(raw []byte, limit uint32) bool {
|
||||
// Check for PEM Encoding.
|
||||
if bytes.HasPrefix(raw, []byte("-----BEGIN PKCS7")) {
|
||||
return true
|
||||
}
|
||||
// Check if DER Encoding is long enough.
|
||||
if len(raw) < 20 {
|
||||
return false
|
||||
}
|
||||
// Magic Bytes for the signedData ASN.1 encoding.
|
||||
startHeader := [][]byte{{0x30, 0x80}, {0x30, 0x81}, {0x30, 0x82}, {0x30, 0x83}, {0x30, 0x84}}
|
||||
signedDataMatch := []byte{0x06, 0x09, 0x2A, 0x86, 0x48, 0x86, 0xF7, 0x0D, 0x01, 0x07}
|
||||
// Check if Header is correct. There are multiple valid headers.
|
||||
for i, match := range startHeader {
|
||||
// If first bytes match, then check for ASN.1 Object Type.
|
||||
if bytes.HasPrefix(raw, match) {
|
||||
if bytes.HasPrefix(raw[i+2:], signedDataMatch) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
@ -0,0 +1,39 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
)
|
||||
|
||||
var (
|
||||
// Woff matches a Web Open Font Format file.
|
||||
Woff = prefix([]byte("wOFF"))
|
||||
// Woff2 matches a Web Open Font Format version 2 file.
|
||||
Woff2 = prefix([]byte("wOF2"))
|
||||
// Otf matches an OpenType font file.
|
||||
Otf = prefix([]byte{0x4F, 0x54, 0x54, 0x4F, 0x00})
|
||||
)
|
||||
|
||||
// Ttf matches a TrueType font file.
|
||||
func Ttf(raw []byte, limit uint32) bool {
|
||||
if !bytes.HasPrefix(raw, []byte{0x00, 0x01, 0x00, 0x00}) {
|
||||
return false
|
||||
}
|
||||
return !MsAccessAce(raw, limit) && !MsAccessMdb(raw, limit)
|
||||
}
|
||||
|
||||
// Eot matches an Embedded OpenType font file.
|
||||
func Eot(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 35 &&
|
||||
bytes.Equal(raw[34:36], []byte{0x4C, 0x50}) &&
|
||||
(bytes.Equal(raw[8:11], []byte{0x02, 0x00, 0x01}) ||
|
||||
bytes.Equal(raw[8:11], []byte{0x01, 0x00, 0x00}) ||
|
||||
bytes.Equal(raw[8:11], []byte{0x02, 0x00, 0x02}))
|
||||
}
|
||||
|
||||
// Ttc matches a TrueType Collection font file.
|
||||
func Ttc(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 7 &&
|
||||
bytes.HasPrefix(raw, []byte("ttcf")) &&
|
||||
(bytes.Equal(raw[4:8], []byte{0x00, 0x01, 0x00, 0x00}) ||
|
||||
bytes.Equal(raw[4:8], []byte{0x00, 0x02, 0x00, 0x00}))
|
||||
}
|
||||
@ -0,0 +1,88 @@
|
||||
package magic
|
||||
|
||||
import "bytes"
|
||||
|
||||
var (
|
||||
// AVIF matches an AV1 Image File Format still or animated.
|
||||
// Wikipedia page seems outdated listing image/avif-sequence for animations.
|
||||
// https://github.com/AOMediaCodec/av1-avif/issues/59
|
||||
AVIF = ftyp([]byte("avif"), []byte("avis"))
|
||||
// Mp4 matches an MP4 file.
|
||||
Mp4 = ftyp(
|
||||
[]byte("avc1"), []byte("dash"), []byte("iso2"), []byte("iso3"),
|
||||
[]byte("iso4"), []byte("iso5"), []byte("iso6"), []byte("isom"),
|
||||
[]byte("mmp4"), []byte("mp41"), []byte("mp42"), []byte("mp4v"),
|
||||
[]byte("mp71"), []byte("MSNV"), []byte("NDAS"), []byte("NDSC"),
|
||||
[]byte("NSDC"), []byte("NSDH"), []byte("NDSM"), []byte("NDSP"),
|
||||
[]byte("NDSS"), []byte("NDXC"), []byte("NDXH"), []byte("NDXM"),
|
||||
[]byte("NDXP"), []byte("NDXS"), []byte("F4V "), []byte("F4P "),
|
||||
)
|
||||
// ThreeGP matches a 3GPP file.
|
||||
ThreeGP = ftyp(
|
||||
[]byte("3gp1"), []byte("3gp2"), []byte("3gp3"), []byte("3gp4"),
|
||||
[]byte("3gp5"), []byte("3gp6"), []byte("3gp7"), []byte("3gs7"),
|
||||
[]byte("3ge6"), []byte("3ge7"), []byte("3gg6"),
|
||||
)
|
||||
// ThreeG2 matches a 3GPP2 file.
|
||||
ThreeG2 = ftyp(
|
||||
[]byte("3g24"), []byte("3g25"), []byte("3g26"), []byte("3g2a"),
|
||||
[]byte("3g2b"), []byte("3g2c"), []byte("KDDI"),
|
||||
)
|
||||
// AMp4 matches an audio MP4 file.
|
||||
AMp4 = ftyp(
|
||||
// audio for Adobe Flash Player 9+
|
||||
[]byte("F4A "), []byte("F4B "),
|
||||
// Apple iTunes AAC-LC (.M4A) Audio
|
||||
[]byte("M4B "), []byte("M4P "),
|
||||
// MPEG-4 (.MP4) for SonyPSP
|
||||
[]byte("MSNV"),
|
||||
// Nero Digital AAC Audio
|
||||
[]byte("NDAS"),
|
||||
)
|
||||
// Mqv matches a Sony / Mobile QuickTime file.
|
||||
Mqv = ftyp([]byte("mqt "))
|
||||
// M4a matches an audio M4A file.
|
||||
M4a = ftyp([]byte("M4A "))
|
||||
// M4v matches an Appl4 M4V video file.
|
||||
M4v = ftyp([]byte("M4V "), []byte("M4VH"), []byte("M4VP"))
|
||||
// Heic matches a High Efficiency Image Coding (HEIC) file.
|
||||
Heic = ftyp([]byte("heic"), []byte("heix"))
|
||||
// HeicSequence matches a High Efficiency Image Coding (HEIC) file sequence.
|
||||
HeicSequence = ftyp([]byte("hevc"), []byte("hevx"))
|
||||
// Heif matches a High Efficiency Image File Format (HEIF) file.
|
||||
Heif = ftyp([]byte("mif1"), []byte("heim"), []byte("heis"), []byte("avic"))
|
||||
// HeifSequence matches a High Efficiency Image File Format (HEIF) file sequence.
|
||||
HeifSequence = ftyp([]byte("msf1"), []byte("hevm"), []byte("hevs"), []byte("avcs"))
|
||||
// TODO: add support for remaining video formats at ftyps.com.
|
||||
)
|
||||
|
||||
// QuickTime matches a QuickTime File Format file.
|
||||
// https://www.loc.gov/preservation/digital/formats/fdd/fdd000052.shtml
|
||||
// https://developer.apple.com/library/archive/documentation/QuickTime/QTFF/QTFFChap1/qtff1.html#//apple_ref/doc/uid/TP40000939-CH203-38190
|
||||
// https://github.com/apache/tika/blob/0f5570691133c75ac4472c3340354a6c4080b104/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml#L7758-L7777
|
||||
func QuickTime(raw []byte, _ uint32) bool {
|
||||
if len(raw) < 12 {
|
||||
return false
|
||||
}
|
||||
// First 4 bytes represent the size of the atom as unsigned int.
|
||||
// Next 4 bytes are the type of the atom.
|
||||
// For `ftyp` atoms check if first byte in size is 0, otherwise, a text file
|
||||
// which happens to contain 'ftypqt ' at index 4 will trigger a false positive.
|
||||
if bytes.Equal(raw[4:12], []byte("ftypqt ")) ||
|
||||
bytes.Equal(raw[4:12], []byte("ftypmoov")) {
|
||||
return raw[0] == 0x00
|
||||
}
|
||||
basicAtomTypes := [][]byte{
|
||||
[]byte("moov\x00"),
|
||||
[]byte("mdat\x00"),
|
||||
[]byte("free\x00"),
|
||||
[]byte("skip\x00"),
|
||||
[]byte("pnot\x00"),
|
||||
}
|
||||
for _, a := range basicAtomTypes {
|
||||
if bytes.Equal(raw[4:9], a) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return bytes.Equal(raw[:8], []byte("\x00\x00\x00\x08wide"))
|
||||
}
|
||||
@ -0,0 +1,55 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
)
|
||||
|
||||
// Shp matches a shape format file.
|
||||
// https://www.esri.com/library/whitepapers/pdfs/shapefile.pdf
|
||||
func Shp(raw []byte, limit uint32) bool {
|
||||
if len(raw) < 112 {
|
||||
return false
|
||||
}
|
||||
|
||||
if !(binary.BigEndian.Uint32(raw[0:4]) == 9994 &&
|
||||
binary.BigEndian.Uint32(raw[4:8]) == 0 &&
|
||||
binary.BigEndian.Uint32(raw[8:12]) == 0 &&
|
||||
binary.BigEndian.Uint32(raw[12:16]) == 0 &&
|
||||
binary.BigEndian.Uint32(raw[16:20]) == 0 &&
|
||||
binary.BigEndian.Uint32(raw[20:24]) == 0 &&
|
||||
binary.LittleEndian.Uint32(raw[28:32]) == 1000) {
|
||||
return false
|
||||
}
|
||||
|
||||
shapeTypes := []int{
|
||||
0, // Null shape
|
||||
1, // Point
|
||||
3, // Polyline
|
||||
5, // Polygon
|
||||
8, // MultiPoint
|
||||
11, // PointZ
|
||||
13, // PolylineZ
|
||||
15, // PolygonZ
|
||||
18, // MultiPointZ
|
||||
21, // PointM
|
||||
23, // PolylineM
|
||||
25, // PolygonM
|
||||
28, // MultiPointM
|
||||
31, // MultiPatch
|
||||
}
|
||||
|
||||
for _, st := range shapeTypes {
|
||||
if st == int(binary.LittleEndian.Uint32(raw[108:112])) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// Shx matches a shape index format file.
|
||||
// https://www.esri.com/library/whitepapers/pdfs/shapefile.pdf
|
||||
func Shx(raw []byte, limit uint32) bool {
|
||||
return bytes.HasPrefix(raw, []byte{0x00, 0x00, 0x27, 0x0A})
|
||||
}
|
||||
@ -0,0 +1,110 @@
|
||||
package magic
|
||||
|
||||
import "bytes"
|
||||
|
||||
var (
|
||||
// Png matches a Portable Network Graphics file.
|
||||
// https://www.w3.org/TR/PNG/
|
||||
Png = prefix([]byte{0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A})
|
||||
// Apng matches an Animated Portable Network Graphics file.
|
||||
// https://wiki.mozilla.org/APNG_Specification
|
||||
Apng = offset([]byte("acTL"), 37)
|
||||
// Jpg matches a Joint Photographic Experts Group file.
|
||||
Jpg = prefix([]byte{0xFF, 0xD8, 0xFF})
|
||||
// Jp2 matches a JPEG 2000 Image file (ISO 15444-1).
|
||||
Jp2 = jpeg2k([]byte{0x6a, 0x70, 0x32, 0x20})
|
||||
// Jpx matches a JPEG 2000 Image file (ISO 15444-2).
|
||||
Jpx = jpeg2k([]byte{0x6a, 0x70, 0x78, 0x20})
|
||||
// Jpm matches a JPEG 2000 Image file (ISO 15444-6).
|
||||
Jpm = jpeg2k([]byte{0x6a, 0x70, 0x6D, 0x20})
|
||||
// Gif matches a Graphics Interchange Format file.
|
||||
Gif = prefix([]byte("GIF87a"), []byte("GIF89a"))
|
||||
// Bmp matches a bitmap image file.
|
||||
Bmp = prefix([]byte{0x42, 0x4D})
|
||||
// Ps matches a PostScript file.
|
||||
Ps = prefix([]byte("%!PS-Adobe-"))
|
||||
// Psd matches a Photoshop Document file.
|
||||
Psd = prefix([]byte("8BPS"))
|
||||
// Ico matches an ICO file.
|
||||
Ico = prefix([]byte{0x00, 0x00, 0x01, 0x00}, []byte{0x00, 0x00, 0x02, 0x00})
|
||||
// Icns matches an ICNS (Apple Icon Image format) file.
|
||||
Icns = prefix([]byte("icns"))
|
||||
// Tiff matches a Tagged Image File Format file.
|
||||
Tiff = prefix([]byte{0x49, 0x49, 0x2A, 0x00}, []byte{0x4D, 0x4D, 0x00, 0x2A})
|
||||
// Bpg matches a Better Portable Graphics file.
|
||||
Bpg = prefix([]byte{0x42, 0x50, 0x47, 0xFB})
|
||||
// Xcf matches GIMP image data.
|
||||
Xcf = prefix([]byte("gimp xcf"))
|
||||
// Pat matches GIMP pattern data.
|
||||
Pat = offset([]byte("GPAT"), 20)
|
||||
// Gbr matches GIMP brush data.
|
||||
Gbr = offset([]byte("GIMP"), 20)
|
||||
// Hdr matches Radiance HDR image.
|
||||
// https://web.archive.org/web/20060913152809/http://local.wasp.uwa.edu.au/~pbourke/dataformats/pic/
|
||||
Hdr = prefix([]byte("#?RADIANCE\n"))
|
||||
// Xpm matches X PixMap image data.
|
||||
Xpm = prefix([]byte{0x2F, 0x2A, 0x20, 0x58, 0x50, 0x4D, 0x20, 0x2A, 0x2F})
|
||||
// Jxs matches a JPEG XS coded image file (ISO/IEC 21122-3).
|
||||
Jxs = prefix([]byte{0x00, 0x00, 0x00, 0x0C, 0x4A, 0x58, 0x53, 0x20, 0x0D, 0x0A, 0x87, 0x0A})
|
||||
// Jxr matches Microsoft HD JXR photo file.
|
||||
Jxr = prefix([]byte{0x49, 0x49, 0xBC, 0x01})
|
||||
)
|
||||
|
||||
func jpeg2k(sig []byte) Detector {
|
||||
return func(raw []byte, _ uint32) bool {
|
||||
if len(raw) < 24 {
|
||||
return false
|
||||
}
|
||||
|
||||
if !bytes.Equal(raw[4:8], []byte{0x6A, 0x50, 0x20, 0x20}) &&
|
||||
!bytes.Equal(raw[4:8], []byte{0x6A, 0x50, 0x32, 0x20}) {
|
||||
return false
|
||||
}
|
||||
return bytes.Equal(raw[20:24], sig)
|
||||
}
|
||||
}
|
||||
|
||||
// Webp matches a WebP file.
|
||||
func Webp(raw []byte, _ uint32) bool {
|
||||
return len(raw) > 12 &&
|
||||
bytes.Equal(raw[0:4], []byte("RIFF")) &&
|
||||
bytes.Equal(raw[8:12], []byte{0x57, 0x45, 0x42, 0x50})
|
||||
}
|
||||
|
||||
// Dwg matches a CAD drawing file.
|
||||
func Dwg(raw []byte, _ uint32) bool {
|
||||
if len(raw) < 6 || raw[0] != 0x41 || raw[1] != 0x43 {
|
||||
return false
|
||||
}
|
||||
dwgVersions := [][]byte{
|
||||
{0x31, 0x2E, 0x34, 0x30},
|
||||
{0x31, 0x2E, 0x35, 0x30},
|
||||
{0x32, 0x2E, 0x31, 0x30},
|
||||
{0x31, 0x30, 0x30, 0x32},
|
||||
{0x31, 0x30, 0x30, 0x33},
|
||||
{0x31, 0x30, 0x30, 0x34},
|
||||
{0x31, 0x30, 0x30, 0x36},
|
||||
{0x31, 0x30, 0x30, 0x39},
|
||||
{0x31, 0x30, 0x31, 0x32},
|
||||
{0x31, 0x30, 0x31, 0x34},
|
||||
{0x31, 0x30, 0x31, 0x35},
|
||||
{0x31, 0x30, 0x31, 0x38},
|
||||
{0x31, 0x30, 0x32, 0x31},
|
||||
{0x31, 0x30, 0x32, 0x34},
|
||||
{0x31, 0x30, 0x33, 0x32},
|
||||
}
|
||||
|
||||
for _, d := range dwgVersions {
|
||||
if bytes.Equal(raw[2:6], d) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// Jxl matches JPEG XL image file.
|
||||
func Jxl(raw []byte, _ uint32) bool {
|
||||
return bytes.HasPrefix(raw, []byte{0xFF, 0x0A}) ||
|
||||
bytes.HasPrefix(raw, []byte("\x00\x00\x00\x0cJXL\x20\x0d\x0a\x87\x0a"))
|
||||
}
|
||||
@ -0,0 +1,225 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
)
|
||||
|
||||
var (
|
||||
xlsxSigFiles = []string{
|
||||
"xl/worksheets/",
|
||||
"xl/drawings/",
|
||||
"xl/theme/",
|
||||
"xl/_rels/",
|
||||
"xl/styles.xml",
|
||||
"xl/workbook.xml",
|
||||
"xl/sharedStrings.xml",
|
||||
}
|
||||
docxSigFiles = []string{
|
||||
"word/media/",
|
||||
"word/_rels/document.xml.rels",
|
||||
"word/document.xml",
|
||||
"word/styles.xml",
|
||||
"word/fontTable.xml",
|
||||
"word/settings.xml",
|
||||
"word/numbering.xml",
|
||||
"word/header",
|
||||
"word/footer",
|
||||
}
|
||||
pptxSigFiles = []string{
|
||||
"ppt/slides/",
|
||||
"ppt/media/",
|
||||
"ppt/slideLayouts/",
|
||||
"ppt/theme/",
|
||||
"ppt/slideMasters/",
|
||||
"ppt/tags/",
|
||||
"ppt/notesMasters/",
|
||||
"ppt/_rels/",
|
||||
"ppt/handoutMasters/",
|
||||
"ppt/notesSlides/",
|
||||
"ppt/presentation.xml",
|
||||
"ppt/tableStyles.xml",
|
||||
"ppt/presProps.xml",
|
||||
"ppt/viewProps.xml",
|
||||
}
|
||||
)
|
||||
|
||||
// Xlsx matches a Microsoft Excel 2007 file.
|
||||
func Xlsx(raw []byte, limit uint32) bool {
|
||||
return zipContains(raw, xlsxSigFiles...)
|
||||
}
|
||||
|
||||
// Docx matches a Microsoft Word 2007 file.
|
||||
func Docx(raw []byte, limit uint32) bool {
|
||||
return zipContains(raw, docxSigFiles...)
|
||||
}
|
||||
|
||||
// Pptx matches a Microsoft PowerPoint 2007 file.
|
||||
func Pptx(raw []byte, limit uint32) bool {
|
||||
return zipContains(raw, pptxSigFiles...)
|
||||
}
|
||||
|
||||
// Ole matches an Open Linking and Embedding file.
|
||||
//
|
||||
// https://en.wikipedia.org/wiki/Object_Linking_and_Embedding
|
||||
func Ole(raw []byte, limit uint32) bool {
|
||||
return bytes.HasPrefix(raw, []byte{0xD0, 0xCF, 0x11, 0xE0, 0xA1, 0xB1, 0x1A, 0xE1})
|
||||
}
|
||||
|
||||
// Aaf matches an Advanced Authoring Format file.
|
||||
// See: https://pyaaf.readthedocs.io/en/latest/about.html
|
||||
// See: https://en.wikipedia.org/wiki/Advanced_Authoring_Format
|
||||
func Aaf(raw []byte, limit uint32) bool {
|
||||
if len(raw) < 31 {
|
||||
return false
|
||||
}
|
||||
return bytes.HasPrefix(raw[8:], []byte{0x41, 0x41, 0x46, 0x42, 0x0D, 0x00, 0x4F, 0x4D}) &&
|
||||
(raw[30] == 0x09 || raw[30] == 0x0C)
|
||||
}
|
||||
|
||||
// Doc matches a Microsoft Word 97-2003 file.
|
||||
// See: https://github.com/decalage2/oletools/blob/412ee36ae45e70f42123e835871bac956d958461/oletools/common/clsid.py
|
||||
func Doc(raw []byte, _ uint32) bool {
|
||||
clsids := [][]byte{
|
||||
// Microsoft Word 97-2003 Document (Word.Document.8)
|
||||
{0x06, 0x09, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46},
|
||||
// Microsoft Word 6.0-7.0 Document (Word.Document.6)
|
||||
{0x00, 0x09, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46},
|
||||
// Microsoft Word Picture (Word.Picture.8)
|
||||
{0x07, 0x09, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46},
|
||||
}
|
||||
|
||||
for _, clsid := range clsids {
|
||||
if matchOleClsid(raw, clsid) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// Ppt matches a Microsoft PowerPoint 97-2003 file or a PowerPoint 95 presentation.
|
||||
func Ppt(raw []byte, limit uint32) bool {
|
||||
// Root CLSID test is the safest way to detect identify OLE, however, the format
|
||||
// often places the root CLSID at the end of the file.
|
||||
if matchOleClsid(raw, []byte{
|
||||
0x10, 0x8d, 0x81, 0x64, 0x9b, 0x4f, 0xcf, 0x11,
|
||||
0x86, 0xea, 0x00, 0xaa, 0x00, 0xb9, 0x29, 0xe8,
|
||||
}) || matchOleClsid(raw, []byte{
|
||||
0x70, 0xae, 0x7b, 0xea, 0x3b, 0xfb, 0xcd, 0x11,
|
||||
0xa9, 0x03, 0x00, 0xaa, 0x00, 0x51, 0x0e, 0xa3,
|
||||
}) {
|
||||
return true
|
||||
}
|
||||
|
||||
lin := len(raw)
|
||||
if lin < 520 {
|
||||
return false
|
||||
}
|
||||
pptSubHeaders := [][]byte{
|
||||
{0xA0, 0x46, 0x1D, 0xF0},
|
||||
{0x00, 0x6E, 0x1E, 0xF0},
|
||||
{0x0F, 0x00, 0xE8, 0x03},
|
||||
}
|
||||
for _, h := range pptSubHeaders {
|
||||
if bytes.HasPrefix(raw[512:], h) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
if bytes.HasPrefix(raw[512:], []byte{0xFD, 0xFF, 0xFF, 0xFF}) &&
|
||||
raw[518] == 0x00 && raw[519] == 0x00 {
|
||||
return true
|
||||
}
|
||||
|
||||
return lin > 1152 && bytes.Contains(raw[1152:min(4096, lin)],
|
||||
[]byte("P\x00o\x00w\x00e\x00r\x00P\x00o\x00i\x00n\x00t\x00 D\x00o\x00c\x00u\x00m\x00e\x00n\x00t"))
|
||||
}
|
||||
|
||||
// Xls matches a Microsoft Excel 97-2003 file.
|
||||
func Xls(raw []byte, limit uint32) bool {
|
||||
// Root CLSID test is the safest way to detect identify OLE, however, the format
|
||||
// often places the root CLSID at the end of the file.
|
||||
if matchOleClsid(raw, []byte{
|
||||
0x10, 0x08, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
}) || matchOleClsid(raw, []byte{
|
||||
0x20, 0x08, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
}) {
|
||||
return true
|
||||
}
|
||||
|
||||
lin := len(raw)
|
||||
if lin < 520 {
|
||||
return false
|
||||
}
|
||||
xlsSubHeaders := [][]byte{
|
||||
{0x09, 0x08, 0x10, 0x00, 0x00, 0x06, 0x05, 0x00},
|
||||
{0xFD, 0xFF, 0xFF, 0xFF, 0x10},
|
||||
{0xFD, 0xFF, 0xFF, 0xFF, 0x1F},
|
||||
{0xFD, 0xFF, 0xFF, 0xFF, 0x22},
|
||||
{0xFD, 0xFF, 0xFF, 0xFF, 0x23},
|
||||
{0xFD, 0xFF, 0xFF, 0xFF, 0x28},
|
||||
{0xFD, 0xFF, 0xFF, 0xFF, 0x29},
|
||||
}
|
||||
for _, h := range xlsSubHeaders {
|
||||
if bytes.HasPrefix(raw[512:], h) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return lin > 1152 && bytes.Contains(raw[1152:min(4096, lin)],
|
||||
[]byte("W\x00k\x00s\x00S\x00S\x00W\x00o\x00r\x00k\x00B\x00o\x00o\x00k"))
|
||||
}
|
||||
|
||||
// Pub matches a Microsoft Publisher file.
|
||||
func Pub(raw []byte, limit uint32) bool {
|
||||
return matchOleClsid(raw, []byte{
|
||||
0x01, 0x12, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46,
|
||||
})
|
||||
}
|
||||
|
||||
// Msg matches a Microsoft Outlook email file.
|
||||
func Msg(raw []byte, limit uint32) bool {
|
||||
return matchOleClsid(raw, []byte{
|
||||
0x0B, 0x0D, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46,
|
||||
})
|
||||
}
|
||||
|
||||
// Msi matches a Microsoft Windows Installer file.
|
||||
// http://fileformats.archiveteam.org/wiki/Microsoft_Compound_File
|
||||
func Msi(raw []byte, limit uint32) bool {
|
||||
return matchOleClsid(raw, []byte{
|
||||
0x84, 0x10, 0x0C, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46,
|
||||
})
|
||||
}
|
||||
|
||||
// Helper to match by a specific CLSID of a compound file.
|
||||
//
|
||||
// http://fileformats.archiveteam.org/wiki/Microsoft_Compound_File
|
||||
func matchOleClsid(in []byte, clsid []byte) bool {
|
||||
// Microsoft Compound files v3 have a sector length of 512, while v4 has 4096.
|
||||
// Change sector offset depending on file version.
|
||||
// https://www.loc.gov/preservation/digital/formats/fdd/fdd000392.shtml
|
||||
sectorLength := 512
|
||||
if len(in) < sectorLength {
|
||||
return false
|
||||
}
|
||||
if in[26] == 0x04 && in[27] == 0x00 {
|
||||
sectorLength = 4096
|
||||
}
|
||||
|
||||
// SecID of first sector of the directory stream.
|
||||
firstSecID := int(binary.LittleEndian.Uint32(in[48:52]))
|
||||
|
||||
// Expected offset of CLSID for root storage object.
|
||||
clsidOffset := sectorLength*(1+firstSecID) + 80
|
||||
|
||||
if len(in) <= clsidOffset+16 {
|
||||
return false
|
||||
}
|
||||
|
||||
return bytes.HasPrefix(in[clsidOffset:], clsid)
|
||||
}
|
||||
@ -0,0 +1,42 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
)
|
||||
|
||||
/*
|
||||
NOTE:
|
||||
|
||||
In May 2003, two Internet RFCs were published relating to the format.
|
||||
The Ogg bitstream was defined in RFC 3533 (which is classified as
|
||||
'informative') and its Internet content type (application/ogg) in RFC
|
||||
3534 (which is, as of 2006, a proposed standard protocol). In
|
||||
September 2008, RFC 3534 was obsoleted by RFC 5334, which added
|
||||
content types video/ogg, audio/ogg and filename extensions .ogx, .ogv,
|
||||
.oga, .spx.
|
||||
|
||||
See:
|
||||
https://tools.ietf.org/html/rfc3533
|
||||
https://developer.mozilla.org/en-US/docs/Web/HTTP/Configuring_servers_for_Ogg_media#Serve_media_with_the_correct_MIME_type
|
||||
https://github.com/file/file/blob/master/magic/Magdir/vorbis
|
||||
*/
|
||||
|
||||
// Ogg matches an Ogg file.
|
||||
func Ogg(raw []byte, limit uint32) bool {
|
||||
return bytes.HasPrefix(raw, []byte("\x4F\x67\x67\x53\x00"))
|
||||
}
|
||||
|
||||
// OggAudio matches an audio ogg file.
|
||||
func OggAudio(raw []byte, limit uint32) bool {
|
||||
return len(raw) >= 37 && (bytes.HasPrefix(raw[28:], []byte("\x7fFLAC")) ||
|
||||
bytes.HasPrefix(raw[28:], []byte("\x01vorbis")) ||
|
||||
bytes.HasPrefix(raw[28:], []byte("OpusHead")) ||
|
||||
bytes.HasPrefix(raw[28:], []byte("Speex\x20\x20\x20")))
|
||||
}
|
||||
|
||||
// OggVideo matches a video ogg file.
|
||||
func OggVideo(raw []byte, limit uint32) bool {
|
||||
return len(raw) >= 37 && (bytes.HasPrefix(raw[28:], []byte("\x80theora")) ||
|
||||
bytes.HasPrefix(raw[28:], []byte("fishead\x00")) ||
|
||||
bytes.HasPrefix(raw[28:], []byte("\x01video\x00\x00\x00"))) // OGM video
|
||||
}
|
||||
@ -0,0 +1,375 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"bytes"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/gabriel-vasile/mimetype/internal/charset"
|
||||
"github.com/gabriel-vasile/mimetype/internal/json"
|
||||
)
|
||||
|
||||
var (
|
||||
// HTML matches a Hypertext Markup Language file.
|
||||
HTML = markup(
|
||||
[]byte("<!DOCTYPE HTML"),
|
||||
[]byte("<HTML"),
|
||||
[]byte("<HEAD"),
|
||||
[]byte("<SCRIPT"),
|
||||
[]byte("<IFRAME"),
|
||||
[]byte("<H1"),
|
||||
[]byte("<DIV"),
|
||||
[]byte("<FONT"),
|
||||
[]byte("<TABLE"),
|
||||
[]byte("<A"),
|
||||
[]byte("<STYLE"),
|
||||
[]byte("<TITLE"),
|
||||
[]byte("<B"),
|
||||
[]byte("<BODY"),
|
||||
[]byte("<BR"),
|
||||
[]byte("<P"),
|
||||
)
|
||||
// XML matches an Extensible Markup Language file.
|
||||
XML = markup([]byte("<?XML"))
|
||||
// Owl2 matches an Owl ontology file.
|
||||
Owl2 = xml(newXMLSig("Ontology", `xmlns="http://www.w3.org/2002/07/owl#"`))
|
||||
// Rss matches a Rich Site Summary file.
|
||||
Rss = xml(newXMLSig("rss", ""))
|
||||
// Atom matches an Atom Syndication Format file.
|
||||
Atom = xml(newXMLSig("feed", `xmlns="http://www.w3.org/2005/Atom"`))
|
||||
// Kml matches a Keyhole Markup Language file.
|
||||
Kml = xml(
|
||||
newXMLSig("kml", `xmlns="http://www.opengis.net/kml/2.2"`),
|
||||
newXMLSig("kml", `xmlns="http://earth.google.com/kml/2.0"`),
|
||||
newXMLSig("kml", `xmlns="http://earth.google.com/kml/2.1"`),
|
||||
newXMLSig("kml", `xmlns="http://earth.google.com/kml/2.2"`),
|
||||
)
|
||||
// Xliff matches a XML Localization Interchange File Format file.
|
||||
Xliff = xml(newXMLSig("xliff", `xmlns="urn:oasis:names:tc:xliff:document:1.2"`))
|
||||
// Collada matches a COLLAborative Design Activity file.
|
||||
Collada = xml(newXMLSig("COLLADA", `xmlns="http://www.collada.org/2005/11/COLLADASchema"`))
|
||||
// Gml matches a Geography Markup Language file.
|
||||
Gml = xml(
|
||||
newXMLSig("", `xmlns:gml="http://www.opengis.net/gml"`),
|
||||
newXMLSig("", `xmlns:gml="http://www.opengis.net/gml/3.2"`),
|
||||
newXMLSig("", `xmlns:gml="http://www.opengis.net/gml/3.3/exr"`),
|
||||
)
|
||||
// Gpx matches a GPS Exchange Format file.
|
||||
Gpx = xml(newXMLSig("gpx", `xmlns="http://www.topografix.com/GPX/1/1"`))
|
||||
// Tcx matches a Training Center XML file.
|
||||
Tcx = xml(newXMLSig("TrainingCenterDatabase", `xmlns="http://www.garmin.com/xmlschemas/TrainingCenterDatabase/v2"`))
|
||||
// X3d matches an Extensible 3D Graphics file.
|
||||
X3d = xml(newXMLSig("X3D", `xmlns:xsd="http://www.w3.org/2001/XMLSchema-instance"`))
|
||||
// Amf matches an Additive Manufacturing XML file.
|
||||
Amf = xml(newXMLSig("amf", ""))
|
||||
// Threemf matches a 3D Manufacturing Format file.
|
||||
Threemf = xml(newXMLSig("model", `xmlns="http://schemas.microsoft.com/3dmanufacturing/core/2015/02"`))
|
||||
// Xfdf matches a XML Forms Data Format file.
|
||||
Xfdf = xml(newXMLSig("xfdf", `xmlns="http://ns.adobe.com/xfdf/"`))
|
||||
// VCard matches a Virtual Contact File.
|
||||
VCard = ciPrefix([]byte("BEGIN:VCARD\n"), []byte("BEGIN:VCARD\r\n"))
|
||||
// ICalendar matches a iCalendar file.
|
||||
ICalendar = ciPrefix([]byte("BEGIN:VCALENDAR\n"), []byte("BEGIN:VCALENDAR\r\n"))
|
||||
phpPageF = ciPrefix(
|
||||
[]byte("<?PHP"),
|
||||
[]byte("<?\n"),
|
||||
[]byte("<?\r"),
|
||||
[]byte("<? "),
|
||||
)
|
||||
phpScriptF = shebang(
|
||||
[]byte("/usr/local/bin/php"),
|
||||
[]byte("/usr/bin/php"),
|
||||
[]byte("/usr/bin/env php"),
|
||||
)
|
||||
// Js matches a Javascript file.
|
||||
Js = shebang(
|
||||
[]byte("/bin/node"),
|
||||
[]byte("/usr/bin/node"),
|
||||
[]byte("/bin/nodejs"),
|
||||
[]byte("/usr/bin/nodejs"),
|
||||
[]byte("/usr/bin/env node"),
|
||||
[]byte("/usr/bin/env nodejs"),
|
||||
)
|
||||
// Lua matches a Lua programming language file.
|
||||
Lua = shebang(
|
||||
[]byte("/usr/bin/lua"),
|
||||
[]byte("/usr/local/bin/lua"),
|
||||
[]byte("/usr/bin/env lua"),
|
||||
)
|
||||
// Perl matches a Perl programming language file.
|
||||
Perl = shebang(
|
||||
[]byte("/usr/bin/perl"),
|
||||
[]byte("/usr/bin/env perl"),
|
||||
)
|
||||
// Python matches a Python programming language file.
|
||||
Python = shebang(
|
||||
[]byte("/usr/bin/python"),
|
||||
[]byte("/usr/local/bin/python"),
|
||||
[]byte("/usr/bin/env python"),
|
||||
)
|
||||
// Tcl matches a Tcl programming language file.
|
||||
Tcl = shebang(
|
||||
[]byte("/usr/bin/tcl"),
|
||||
[]byte("/usr/local/bin/tcl"),
|
||||
[]byte("/usr/bin/env tcl"),
|
||||
[]byte("/usr/bin/tclsh"),
|
||||
[]byte("/usr/local/bin/tclsh"),
|
||||
[]byte("/usr/bin/env tclsh"),
|
||||
[]byte("/usr/bin/wish"),
|
||||
[]byte("/usr/local/bin/wish"),
|
||||
[]byte("/usr/bin/env wish"),
|
||||
)
|
||||
// Rtf matches a Rich Text Format file.
|
||||
Rtf = prefix([]byte("{\\rtf1"))
|
||||
)
|
||||
|
||||
// Text matches a plain text file.
|
||||
//
|
||||
// TODO: This function does not parse BOM-less UTF16 and UTF32 files. Not really
|
||||
// sure it should. Linux file utility also requires a BOM for UTF16 and UTF32.
|
||||
func Text(raw []byte, limit uint32) bool {
|
||||
// First look for BOM.
|
||||
if cset := charset.FromBOM(raw); cset != "" {
|
||||
return true
|
||||
}
|
||||
// Binary data bytes as defined here: https://mimesniff.spec.whatwg.org/#binary-data-byte
|
||||
for _, b := range raw {
|
||||
if b <= 0x08 ||
|
||||
b == 0x0B ||
|
||||
0x0E <= b && b <= 0x1A ||
|
||||
0x1C <= b && b <= 0x1F {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// Php matches a PHP: Hypertext Preprocessor file.
|
||||
func Php(raw []byte, limit uint32) bool {
|
||||
if res := phpPageF(raw, limit); res {
|
||||
return res
|
||||
}
|
||||
return phpScriptF(raw, limit)
|
||||
}
|
||||
|
||||
// JSON matches a JavaScript Object Notation file.
|
||||
func JSON(raw []byte, limit uint32) bool {
|
||||
raw = trimLWS(raw)
|
||||
// #175 A single JSON string, number or bool is not considered JSON.
|
||||
// JSON objects and arrays are reported as JSON.
|
||||
if len(raw) < 2 || (raw[0] != '[' && raw[0] != '{') {
|
||||
return false
|
||||
}
|
||||
parsed, err := json.Scan(raw)
|
||||
// If the full file content was provided, check there is no error.
|
||||
if limit == 0 || len(raw) < int(limit) {
|
||||
return err == nil
|
||||
}
|
||||
|
||||
// If a section of the file was provided, check if all of it was parsed.
|
||||
return parsed == len(raw) && len(raw) > 0
|
||||
}
|
||||
|
||||
// GeoJSON matches a RFC 7946 GeoJSON file.
|
||||
//
|
||||
// GeoJSON detection implies searching for key:value pairs like: `"type": "Feature"`
|
||||
// in the input.
|
||||
// BUG(gabriel-vasile): The "type" key should be searched for in the root object.
|
||||
func GeoJSON(raw []byte, limit uint32) bool {
|
||||
raw = trimLWS(raw)
|
||||
if len(raw) == 0 {
|
||||
return false
|
||||
}
|
||||
// GeoJSON is always a JSON object, not a JSON array or any other JSON value.
|
||||
if raw[0] != '{' {
|
||||
return false
|
||||
}
|
||||
|
||||
s := []byte(`"type"`)
|
||||
si, sl := bytes.Index(raw, s), len(s)
|
||||
|
||||
if si == -1 {
|
||||
return false
|
||||
}
|
||||
|
||||
// If the "type" string is the suffix of the input,
|
||||
// there is no need to search for the value of the key.
|
||||
if si+sl == len(raw) {
|
||||
return false
|
||||
}
|
||||
// Skip the "type" part.
|
||||
raw = raw[si+sl:]
|
||||
// Skip any whitespace before the colon.
|
||||
raw = trimLWS(raw)
|
||||
// Check for colon.
|
||||
if len(raw) == 0 || raw[0] != ':' {
|
||||
return false
|
||||
}
|
||||
// Skip any whitespace after the colon.
|
||||
raw = trimLWS(raw[1:])
|
||||
|
||||
geoJSONTypes := [][]byte{
|
||||
[]byte(`"Feature"`),
|
||||
[]byte(`"FeatureCollection"`),
|
||||
[]byte(`"Point"`),
|
||||
[]byte(`"LineString"`),
|
||||
[]byte(`"Polygon"`),
|
||||
[]byte(`"MultiPoint"`),
|
||||
[]byte(`"MultiLineString"`),
|
||||
[]byte(`"MultiPolygon"`),
|
||||
[]byte(`"GeometryCollection"`),
|
||||
}
|
||||
for _, t := range geoJSONTypes {
|
||||
if bytes.HasPrefix(raw, t) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// NdJSON matches a Newline delimited JSON file. All complete lines from raw
|
||||
// must be valid JSON documents meaning they contain one of the valid JSON data
|
||||
// types.
|
||||
func NdJSON(raw []byte, limit uint32) bool {
|
||||
lCount, hasObjOrArr := 0, false
|
||||
sc := bufio.NewScanner(dropLastLine(raw, limit))
|
||||
for sc.Scan() {
|
||||
l := sc.Bytes()
|
||||
// Empty lines are allowed in NDJSON.
|
||||
if l = trimRWS(trimLWS(l)); len(l) == 0 {
|
||||
continue
|
||||
}
|
||||
_, err := json.Scan(l)
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
if l[0] == '[' || l[0] == '{' {
|
||||
hasObjOrArr = true
|
||||
}
|
||||
lCount++
|
||||
}
|
||||
|
||||
return lCount > 1 && hasObjOrArr
|
||||
}
|
||||
|
||||
// HAR matches a HAR Spec file.
|
||||
// Spec: http://www.softwareishard.com/blog/har-12-spec/
|
||||
func HAR(raw []byte, limit uint32) bool {
|
||||
s := []byte(`"log"`)
|
||||
si, sl := bytes.Index(raw, s), len(s)
|
||||
|
||||
if si == -1 {
|
||||
return false
|
||||
}
|
||||
|
||||
// If the "log" string is the suffix of the input,
|
||||
// there is no need to search for the value of the key.
|
||||
if si+sl == len(raw) {
|
||||
return false
|
||||
}
|
||||
// Skip the "log" part.
|
||||
raw = raw[si+sl:]
|
||||
// Skip any whitespace before the colon.
|
||||
raw = trimLWS(raw)
|
||||
// Check for colon.
|
||||
if len(raw) == 0 || raw[0] != ':' {
|
||||
return false
|
||||
}
|
||||
// Skip any whitespace after the colon.
|
||||
raw = trimLWS(raw[1:])
|
||||
|
||||
harJSONTypes := [][]byte{
|
||||
[]byte(`"version"`),
|
||||
[]byte(`"creator"`),
|
||||
[]byte(`"entries"`),
|
||||
}
|
||||
for _, t := range harJSONTypes {
|
||||
si := bytes.Index(raw, t)
|
||||
if si > -1 {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// Svg matches a SVG file.
|
||||
func Svg(raw []byte, limit uint32) bool {
|
||||
return bytes.Contains(raw, []byte("<svg"))
|
||||
}
|
||||
|
||||
// Srt matches a SubRip file.
|
||||
func Srt(in []byte, _ uint32) bool {
|
||||
s := bufio.NewScanner(bytes.NewReader(in))
|
||||
if !s.Scan() {
|
||||
return false
|
||||
}
|
||||
// First line must be 1.
|
||||
if s.Text() != "1" {
|
||||
return false
|
||||
}
|
||||
|
||||
if !s.Scan() {
|
||||
return false
|
||||
}
|
||||
secondLine := s.Text()
|
||||
// Timestamp format (e.g: 00:02:16,612 --> 00:02:19,376) limits secondLine
|
||||
// length to exactly 29 characters.
|
||||
if len(secondLine) != 29 {
|
||||
return false
|
||||
}
|
||||
// Decimal separator of fractional seconds in the timestamps must be a
|
||||
// comma, not a period.
|
||||
if strings.Contains(secondLine, ".") {
|
||||
return false
|
||||
}
|
||||
// For Go <1.17, comma is not recognised as a decimal separator by `time.Parse`.
|
||||
secondLine = strings.ReplaceAll(secondLine, ",", ".")
|
||||
// Second line must be a time range.
|
||||
ts := strings.Split(secondLine, " --> ")
|
||||
if len(ts) != 2 {
|
||||
return false
|
||||
}
|
||||
const layout = "15:04:05.000"
|
||||
t0, err := time.Parse(layout, ts[0])
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
t1, err := time.Parse(layout, ts[1])
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
if t0.After(t1) {
|
||||
return false
|
||||
}
|
||||
|
||||
// A third line must exist and not be empty. This is the actual subtitle text.
|
||||
return s.Scan() && len(s.Bytes()) != 0
|
||||
}
|
||||
|
||||
// Vtt matches a Web Video Text Tracks (WebVTT) file. See
|
||||
// https://www.iana.org/assignments/media-types/text/vtt.
|
||||
func Vtt(raw []byte, limit uint32) bool {
|
||||
// Prefix match.
|
||||
prefixes := [][]byte{
|
||||
{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0A}, // UTF-8 BOM, "WEBVTT" and a line feed
|
||||
{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0D}, // UTF-8 BOM, "WEBVTT" and a carriage return
|
||||
{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x20}, // UTF-8 BOM, "WEBVTT" and a space
|
||||
{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x09}, // UTF-8 BOM, "WEBVTT" and a horizontal tab
|
||||
{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0A}, // "WEBVTT" and a line feed
|
||||
{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0D}, // "WEBVTT" and a carriage return
|
||||
{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x20}, // "WEBVTT" and a space
|
||||
{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x09}, // "WEBVTT" and a horizontal tab
|
||||
}
|
||||
for _, p := range prefixes {
|
||||
if bytes.HasPrefix(raw, p) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
// Exact match.
|
||||
return bytes.Equal(raw, []byte{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54}) || // UTF-8 BOM and "WEBVTT"
|
||||
bytes.Equal(raw, []byte{0x57, 0x45, 0x42, 0x56, 0x54, 0x54}) // "WEBVTT"
|
||||
}
|
||||
@ -0,0 +1,51 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/csv"
|
||||
"io"
|
||||
)
|
||||
|
||||
// Csv matches a comma-separated values file.
|
||||
func Csv(raw []byte, limit uint32) bool {
|
||||
return sv(raw, ',', limit)
|
||||
}
|
||||
|
||||
// Tsv matches a tab-separated values file.
|
||||
func Tsv(raw []byte, limit uint32) bool {
|
||||
return sv(raw, '\t', limit)
|
||||
}
|
||||
|
||||
func sv(in []byte, comma rune, limit uint32) bool {
|
||||
r := csv.NewReader(dropLastLine(in, limit))
|
||||
r.Comma = comma
|
||||
r.TrimLeadingSpace = true
|
||||
r.LazyQuotes = true
|
||||
r.Comment = '#'
|
||||
|
||||
lines, err := r.ReadAll()
|
||||
return err == nil && r.FieldsPerRecord > 1 && len(lines) > 1
|
||||
}
|
||||
|
||||
// dropLastLine drops the last incomplete line from b.
|
||||
//
|
||||
// mimetype limits itself to ReadLimit bytes when performing a detection.
|
||||
// This means, for file formats like CSV for NDJSON, the last line of the input
|
||||
// can be an incomplete line.
|
||||
func dropLastLine(b []byte, cutAt uint32) io.Reader {
|
||||
if cutAt == 0 {
|
||||
return bytes.NewReader(b)
|
||||
}
|
||||
if uint32(len(b)) >= cutAt {
|
||||
for i := cutAt - 1; i > 0; i-- {
|
||||
if b[i] == '\n' {
|
||||
return bytes.NewReader(b[:i])
|
||||
}
|
||||
}
|
||||
|
||||
// No newline was found between the 0 index and cutAt.
|
||||
return bytes.NewReader(b[:cutAt])
|
||||
}
|
||||
|
||||
return bytes.NewReader(b)
|
||||
}
|
||||
@ -0,0 +1,85 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
)
|
||||
|
||||
var (
|
||||
// Flv matches a Flash video file.
|
||||
Flv = prefix([]byte("\x46\x4C\x56\x01"))
|
||||
// Asf matches an Advanced Systems Format file.
|
||||
Asf = prefix([]byte{
|
||||
0x30, 0x26, 0xB2, 0x75, 0x8E, 0x66, 0xCF, 0x11,
|
||||
0xA6, 0xD9, 0x00, 0xAA, 0x00, 0x62, 0xCE, 0x6C,
|
||||
})
|
||||
// Rmvb matches a RealMedia Variable Bitrate file.
|
||||
Rmvb = prefix([]byte{0x2E, 0x52, 0x4D, 0x46})
|
||||
)
|
||||
|
||||
// WebM matches a WebM file.
|
||||
func WebM(raw []byte, limit uint32) bool {
|
||||
return isMatroskaFileTypeMatched(raw, "webm")
|
||||
}
|
||||
|
||||
// Mkv matches a mkv file.
|
||||
func Mkv(raw []byte, limit uint32) bool {
|
||||
return isMatroskaFileTypeMatched(raw, "matroska")
|
||||
}
|
||||
|
||||
// isMatroskaFileTypeMatched is used for webm and mkv file matching.
|
||||
// It checks for .Eߣ sequence. If the sequence is found,
|
||||
// then it means it is Matroska media container, including WebM.
|
||||
// Then it verifies which of the file type it is representing by matching the
|
||||
// file specific string.
|
||||
func isMatroskaFileTypeMatched(in []byte, flType string) bool {
|
||||
if bytes.HasPrefix(in, []byte("\x1A\x45\xDF\xA3")) {
|
||||
return isFileTypeNamePresent(in, flType)
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// isFileTypeNamePresent accepts the matroska input data stream and searches
|
||||
// for the given file type in the stream. Return whether a match is found.
|
||||
// The logic of search is: find first instance of \x42\x82 and then
|
||||
// search for given string after n bytes of above instance.
|
||||
func isFileTypeNamePresent(in []byte, flType string) bool {
|
||||
ind, maxInd, lenIn := 0, 4096, len(in)
|
||||
if lenIn < maxInd { // restricting length to 4096
|
||||
maxInd = lenIn
|
||||
}
|
||||
ind = bytes.Index(in[:maxInd], []byte("\x42\x82"))
|
||||
if ind > 0 && lenIn > ind+2 {
|
||||
ind += 2
|
||||
|
||||
// filetype name will be present exactly
|
||||
// n bytes after the match of the two bytes "\x42\x82"
|
||||
n := vintWidth(int(in[ind]))
|
||||
if lenIn > ind+n {
|
||||
return bytes.HasPrefix(in[ind+n:], []byte(flType))
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// vintWidth parses the variable-integer width in matroska containers
|
||||
func vintWidth(v int) int {
|
||||
mask, max, num := 128, 8, 1
|
||||
for num < max && v&mask == 0 {
|
||||
mask = mask >> 1
|
||||
num++
|
||||
}
|
||||
return num
|
||||
}
|
||||
|
||||
// Mpeg matches a Moving Picture Experts Group file.
|
||||
func Mpeg(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 3 && bytes.HasPrefix(raw, []byte{0x00, 0x00, 0x01}) &&
|
||||
raw[3] >= 0xB0 && raw[3] <= 0xBF
|
||||
}
|
||||
|
||||
// Avi matches an Audio Video Interleaved file.
|
||||
func Avi(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 16 &&
|
||||
bytes.Equal(raw[:4], []byte("RIFF")) &&
|
||||
bytes.Equal(raw[8:16], []byte("AVI LIST"))
|
||||
}
|
||||
@ -0,0 +1,92 @@
|
||||
package magic
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
"strings"
|
||||
)
|
||||
|
||||
var (
|
||||
// Odt matches an OpenDocument Text file.
|
||||
Odt = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.text"), 30)
|
||||
// Ott matches an OpenDocument Text Template file.
|
||||
Ott = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.text-template"), 30)
|
||||
// Ods matches an OpenDocument Spreadsheet file.
|
||||
Ods = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.spreadsheet"), 30)
|
||||
// Ots matches an OpenDocument Spreadsheet Template file.
|
||||
Ots = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.spreadsheet-template"), 30)
|
||||
// Odp matches an OpenDocument Presentation file.
|
||||
Odp = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.presentation"), 30)
|
||||
// Otp matches an OpenDocument Presentation Template file.
|
||||
Otp = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.presentation-template"), 30)
|
||||
// Odg matches an OpenDocument Drawing file.
|
||||
Odg = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.graphics"), 30)
|
||||
// Otg matches an OpenDocument Drawing Template file.
|
||||
Otg = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.graphics-template"), 30)
|
||||
// Odf matches an OpenDocument Formula file.
|
||||
Odf = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.formula"), 30)
|
||||
// Odc matches an OpenDocument Chart file.
|
||||
Odc = offset([]byte("mimetypeapplication/vnd.oasis.opendocument.chart"), 30)
|
||||
// Epub matches an EPUB file.
|
||||
Epub = offset([]byte("mimetypeapplication/epub+zip"), 30)
|
||||
// Sxc matches an OpenOffice Spreadsheet file.
|
||||
Sxc = offset([]byte("mimetypeapplication/vnd.sun.xml.calc"), 30)
|
||||
)
|
||||
|
||||
// Zip matches a zip archive.
|
||||
func Zip(raw []byte, limit uint32) bool {
|
||||
return len(raw) > 3 &&
|
||||
raw[0] == 0x50 && raw[1] == 0x4B &&
|
||||
(raw[2] == 0x3 || raw[2] == 0x5 || raw[2] == 0x7) &&
|
||||
(raw[3] == 0x4 || raw[3] == 0x6 || raw[3] == 0x8)
|
||||
}
|
||||
|
||||
// Jar matches a Java archive file.
|
||||
func Jar(raw []byte, limit uint32) bool {
|
||||
return zipContains(raw, "META-INF/MANIFEST.MF")
|
||||
}
|
||||
|
||||
// zipTokenizer holds the source zip file and scanned index.
|
||||
type zipTokenizer struct {
|
||||
in []byte
|
||||
i int // current index
|
||||
}
|
||||
|
||||
// next returns the next file name from the zip headers.
|
||||
// https://web.archive.org/web/20191129114319/https://users.cs.jmu.edu/buchhofp/forensics/formats/pkzip.html
|
||||
func (t *zipTokenizer) next() (fileName string) {
|
||||
if t.i > len(t.in) {
|
||||
return
|
||||
}
|
||||
in := t.in[t.i:]
|
||||
// pkSig is the signature of the zip local file header.
|
||||
pkSig := []byte("PK\003\004")
|
||||
pkIndex := bytes.Index(in, pkSig)
|
||||
// 30 is the offset of the file name in the header.
|
||||
fNameOffset := pkIndex + 30
|
||||
// end if signature not found or file name offset outside of file.
|
||||
if pkIndex == -1 || fNameOffset > len(in) {
|
||||
return
|
||||
}
|
||||
|
||||
fNameLen := int(binary.LittleEndian.Uint16(in[pkIndex+26 : pkIndex+28]))
|
||||
if fNameLen <= 0 || fNameOffset+fNameLen > len(in) {
|
||||
return
|
||||
}
|
||||
t.i += fNameOffset + fNameLen
|
||||
return string(in[fNameOffset : fNameOffset+fNameLen])
|
||||
}
|
||||
|
||||
// zipContains returns true if the zip file headers from in contain any of the paths.
|
||||
func zipContains(in []byte, paths ...string) bool {
|
||||
t := zipTokenizer{in: in}
|
||||
for i, tok := 0, t.next(); tok != ""; i, tok = i+1, t.next() {
|
||||
for p := range paths {
|
||||
if strings.HasPrefix(tok, paths[p]) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
@ -0,0 +1,186 @@
|
||||
package mimetype
|
||||
|
||||
import (
|
||||
"mime"
|
||||
|
||||
"github.com/gabriel-vasile/mimetype/internal/charset"
|
||||
"github.com/gabriel-vasile/mimetype/internal/magic"
|
||||
)
|
||||
|
||||
// MIME struct holds information about a file format: the string representation
|
||||
// of the MIME type, the extension and the parent file format.
|
||||
type MIME struct {
|
||||
mime string
|
||||
aliases []string
|
||||
extension string
|
||||
// detector receives the raw input and a limit for the number of bytes it is
|
||||
// allowed to check. It returns whether the input matches a signature or not.
|
||||
detector magic.Detector
|
||||
children []*MIME
|
||||
parent *MIME
|
||||
}
|
||||
|
||||
// String returns the string representation of the MIME type, e.g., "application/zip".
|
||||
func (m *MIME) String() string {
|
||||
return m.mime
|
||||
}
|
||||
|
||||
// Extension returns the file extension associated with the MIME type.
|
||||
// It includes the leading dot, as in ".html". When the file format does not
|
||||
// have an extension, the empty string is returned.
|
||||
func (m *MIME) Extension() string {
|
||||
return m.extension
|
||||
}
|
||||
|
||||
// Parent returns the parent MIME type from the hierarchy.
|
||||
// Each MIME type has a non-nil parent, except for the root MIME type.
|
||||
//
|
||||
// For example, the application/json and text/html MIME types have text/plain as
|
||||
// their parent because they are text files who happen to contain JSON or HTML.
|
||||
// Another example is the ZIP format, which is used as container
|
||||
// for Microsoft Office files, EPUB files, JAR files, and others.
|
||||
func (m *MIME) Parent() *MIME {
|
||||
return m.parent
|
||||
}
|
||||
|
||||
// Is checks whether this MIME type, or any of its aliases, is equal to the
|
||||
// expected MIME type. MIME type equality test is done on the "type/subtype"
|
||||
// section, ignores any optional MIME parameters, ignores any leading and
|
||||
// trailing whitespace, and is case insensitive.
|
||||
func (m *MIME) Is(expectedMIME string) bool {
|
||||
// Parsing is needed because some detected MIME types contain parameters
|
||||
// that need to be stripped for the comparison.
|
||||
expectedMIME, _, _ = mime.ParseMediaType(expectedMIME)
|
||||
found, _, _ := mime.ParseMediaType(m.mime)
|
||||
|
||||
if expectedMIME == found {
|
||||
return true
|
||||
}
|
||||
|
||||
for _, alias := range m.aliases {
|
||||
if alias == expectedMIME {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
func newMIME(
|
||||
mime, extension string,
|
||||
detector magic.Detector,
|
||||
children ...*MIME) *MIME {
|
||||
m := &MIME{
|
||||
mime: mime,
|
||||
extension: extension,
|
||||
detector: detector,
|
||||
children: children,
|
||||
}
|
||||
|
||||
for _, c := range children {
|
||||
c.parent = m
|
||||
}
|
||||
|
||||
return m
|
||||
}
|
||||
|
||||
func (m *MIME) alias(aliases ...string) *MIME {
|
||||
m.aliases = aliases
|
||||
return m
|
||||
}
|
||||
|
||||
// match does a depth-first search on the signature tree. It returns the deepest
|
||||
// successful node for which all the children detection functions fail.
|
||||
func (m *MIME) match(in []byte, readLimit uint32) *MIME {
|
||||
for _, c := range m.children {
|
||||
if c.detector(in, readLimit) {
|
||||
return c.match(in, readLimit)
|
||||
}
|
||||
}
|
||||
|
||||
needsCharset := map[string]func([]byte) string{
|
||||
"text/plain": charset.FromPlain,
|
||||
"text/html": charset.FromHTML,
|
||||
"text/xml": charset.FromXML,
|
||||
}
|
||||
// ps holds optional MIME parameters.
|
||||
ps := map[string]string{}
|
||||
if f, ok := needsCharset[m.mime]; ok {
|
||||
if cset := f(in); cset != "" {
|
||||
ps["charset"] = cset
|
||||
}
|
||||
}
|
||||
|
||||
return m.cloneHierarchy(ps)
|
||||
}
|
||||
|
||||
// flatten transforms an hierarchy of MIMEs into a slice of MIMEs.
|
||||
func (m *MIME) flatten() []*MIME {
|
||||
out := []*MIME{m}
|
||||
for _, c := range m.children {
|
||||
out = append(out, c.flatten()...)
|
||||
}
|
||||
|
||||
return out
|
||||
}
|
||||
|
||||
// clone creates a new MIME with the provided optional MIME parameters.
|
||||
func (m *MIME) clone(ps map[string]string) *MIME {
|
||||
clonedMIME := m.mime
|
||||
if len(ps) > 0 {
|
||||
clonedMIME = mime.FormatMediaType(m.mime, ps)
|
||||
}
|
||||
|
||||
return &MIME{
|
||||
mime: clonedMIME,
|
||||
aliases: m.aliases,
|
||||
extension: m.extension,
|
||||
}
|
||||
}
|
||||
|
||||
// cloneHierarchy creates a clone of m and all its ancestors. The optional MIME
|
||||
// parameters are set on the last child of the hierarchy.
|
||||
func (m *MIME) cloneHierarchy(ps map[string]string) *MIME {
|
||||
ret := m.clone(ps)
|
||||
lastChild := ret
|
||||
for p := m.Parent(); p != nil; p = p.Parent() {
|
||||
pClone := p.clone(nil)
|
||||
lastChild.parent = pClone
|
||||
lastChild = pClone
|
||||
}
|
||||
|
||||
return ret
|
||||
}
|
||||
|
||||
func (m *MIME) lookup(mime string) *MIME {
|
||||
for _, n := range append(m.aliases, m.mime) {
|
||||
if n == mime {
|
||||
return m
|
||||
}
|
||||
}
|
||||
|
||||
for _, c := range m.children {
|
||||
if m := c.lookup(mime); m != nil {
|
||||
return m
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Extend adds detection for a sub-format. The detector is a function
|
||||
// returning true when the raw input file satisfies a signature.
|
||||
// The sub-format will be detected if all the detectors in the parent chain return true.
|
||||
// The extension should include the leading dot, as in ".html".
|
||||
func (m *MIME) Extend(detector func(raw []byte, limit uint32) bool, mime, extension string, aliases ...string) {
|
||||
c := &MIME{
|
||||
mime: mime,
|
||||
extension: extension,
|
||||
detector: detector,
|
||||
parent: m,
|
||||
aliases: aliases,
|
||||
}
|
||||
|
||||
mu.Lock()
|
||||
m.children = append([]*MIME{c}, m.children...)
|
||||
mu.Unlock()
|
||||
}
|
||||
|
After Width: | Height: | Size: 1.3 MiB |
@ -0,0 +1,123 @@
|
||||
// Package mimetype uses magic number signatures to detect the MIME type of a file.
|
||||
//
|
||||
// File formats are stored in a hierarchy with application/octet-stream at its root.
|
||||
// For example, the hierarchy for HTML format is application/octet-stream ->
|
||||
// text/plain -> text/html.
|
||||
package mimetype
|
||||
|
||||
import (
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"mime"
|
||||
"os"
|
||||
"sync/atomic"
|
||||
)
|
||||
|
||||
// readLimit is the maximum number of bytes from the input used when detecting.
|
||||
var readLimit uint32 = 3072
|
||||
|
||||
// Detect returns the MIME type found from the provided byte slice.
|
||||
//
|
||||
// The result is always a valid MIME type, with application/octet-stream
|
||||
// returned when identification failed.
|
||||
func Detect(in []byte) *MIME {
|
||||
// Using atomic because readLimit can be written at the same time in other goroutine.
|
||||
l := atomic.LoadUint32(&readLimit)
|
||||
if l > 0 && len(in) > int(l) {
|
||||
in = in[:l]
|
||||
}
|
||||
mu.RLock()
|
||||
defer mu.RUnlock()
|
||||
return root.match(in, l)
|
||||
}
|
||||
|
||||
// DetectReader returns the MIME type of the provided reader.
|
||||
//
|
||||
// The result is always a valid MIME type, with application/octet-stream
|
||||
// returned when identification failed with or without an error.
|
||||
// Any error returned is related to the reading from the input reader.
|
||||
//
|
||||
// DetectReader assumes the reader offset is at the start. If the input is an
|
||||
// io.ReadSeeker you previously read from, it should be rewinded before detection:
|
||||
// reader.Seek(0, io.SeekStart)
|
||||
func DetectReader(r io.Reader) (*MIME, error) {
|
||||
var in []byte
|
||||
var err error
|
||||
|
||||
// Using atomic because readLimit can be written at the same time in other goroutine.
|
||||
l := atomic.LoadUint32(&readLimit)
|
||||
if l == 0 {
|
||||
in, err = ioutil.ReadAll(r)
|
||||
if err != nil {
|
||||
return errMIME, err
|
||||
}
|
||||
} else {
|
||||
var n int
|
||||
in = make([]byte, l)
|
||||
// io.UnexpectedEOF means len(r) < len(in). It is not an error in this case,
|
||||
// it just means the input file is smaller than the allocated bytes slice.
|
||||
n, err = io.ReadFull(r, in)
|
||||
if err != nil && err != io.EOF && err != io.ErrUnexpectedEOF {
|
||||
return errMIME, err
|
||||
}
|
||||
in = in[:n]
|
||||
}
|
||||
|
||||
mu.RLock()
|
||||
defer mu.RUnlock()
|
||||
return root.match(in, l), nil
|
||||
}
|
||||
|
||||
// DetectFile returns the MIME type of the provided file.
|
||||
//
|
||||
// The result is always a valid MIME type, with application/octet-stream
|
||||
// returned when identification failed with or without an error.
|
||||
// Any error returned is related to the opening and reading from the input file.
|
||||
func DetectFile(path string) (*MIME, error) {
|
||||
f, err := os.Open(path)
|
||||
if err != nil {
|
||||
return errMIME, err
|
||||
}
|
||||
defer f.Close()
|
||||
|
||||
return DetectReader(f)
|
||||
}
|
||||
|
||||
// EqualsAny reports whether s MIME type is equal to any MIME type in mimes.
|
||||
// MIME type equality test is done on the "type/subtype" section, ignores
|
||||
// any optional MIME parameters, ignores any leading and trailing whitespace,
|
||||
// and is case insensitive.
|
||||
func EqualsAny(s string, mimes ...string) bool {
|
||||
s, _, _ = mime.ParseMediaType(s)
|
||||
for _, m := range mimes {
|
||||
m, _, _ = mime.ParseMediaType(m)
|
||||
if s == m {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// SetLimit sets the maximum number of bytes read from input when detecting the MIME type.
|
||||
// Increasing the limit provides better detection for file formats which store
|
||||
// their magical numbers towards the end of the file: docx, pptx, xlsx, etc.
|
||||
// A limit of 0 means the whole input file will be used.
|
||||
func SetLimit(limit uint32) {
|
||||
// Using atomic because readLimit can be read at the same time in other goroutine.
|
||||
atomic.StoreUint32(&readLimit, limit)
|
||||
}
|
||||
|
||||
// Extend adds detection for other file formats.
|
||||
// It is equivalent to calling Extend() on the root mime type "application/octet-stream".
|
||||
func Extend(detector func(raw []byte, limit uint32) bool, mime, extension string, aliases ...string) {
|
||||
root.Extend(detector, mime, extension, aliases...)
|
||||
}
|
||||
|
||||
// Lookup finds a MIME object by its string representation.
|
||||
// The representation can be the main mime type, or any of its aliases.
|
||||
func Lookup(mime string) *MIME {
|
||||
mu.RLock()
|
||||
defer mu.RUnlock()
|
||||
return root.lookup(mime)
|
||||
}
|
||||
@ -0,0 +1,178 @@
|
||||
## 172 Supported MIME types
|
||||
This file is automatically generated when running tests. Do not edit manually.
|
||||
|
||||
Extension | MIME type | Aliases
|
||||
--------- | --------- | -------
|
||||
**n/a** | application/octet-stream | -
|
||||
**.xpm** | image/x-xpixmap | -
|
||||
**.7z** | application/x-7z-compressed | -
|
||||
**.zip** | application/zip | application/x-zip, application/x-zip-compressed
|
||||
**.xlsx** | application/vnd.openxmlformats-officedocument.spreadsheetml.sheet | -
|
||||
**.docx** | application/vnd.openxmlformats-officedocument.wordprocessingml.document | -
|
||||
**.pptx** | application/vnd.openxmlformats-officedocument.presentationml.presentation | -
|
||||
**.epub** | application/epub+zip | -
|
||||
**.jar** | application/jar | -
|
||||
**.odt** | application/vnd.oasis.opendocument.text | application/x-vnd.oasis.opendocument.text
|
||||
**.ott** | application/vnd.oasis.opendocument.text-template | application/x-vnd.oasis.opendocument.text-template
|
||||
**.ods** | application/vnd.oasis.opendocument.spreadsheet | application/x-vnd.oasis.opendocument.spreadsheet
|
||||
**.ots** | application/vnd.oasis.opendocument.spreadsheet-template | application/x-vnd.oasis.opendocument.spreadsheet-template
|
||||
**.odp** | application/vnd.oasis.opendocument.presentation | application/x-vnd.oasis.opendocument.presentation
|
||||
**.otp** | application/vnd.oasis.opendocument.presentation-template | application/x-vnd.oasis.opendocument.presentation-template
|
||||
**.odg** | application/vnd.oasis.opendocument.graphics | application/x-vnd.oasis.opendocument.graphics
|
||||
**.otg** | application/vnd.oasis.opendocument.graphics-template | application/x-vnd.oasis.opendocument.graphics-template
|
||||
**.odf** | application/vnd.oasis.opendocument.formula | application/x-vnd.oasis.opendocument.formula
|
||||
**.odc** | application/vnd.oasis.opendocument.chart | application/x-vnd.oasis.opendocument.chart
|
||||
**.sxc** | application/vnd.sun.xml.calc | -
|
||||
**.pdf** | application/pdf | application/x-pdf
|
||||
**.fdf** | application/vnd.fdf | -
|
||||
**n/a** | application/x-ole-storage | -
|
||||
**.msi** | application/x-ms-installer | application/x-windows-installer, application/x-msi
|
||||
**.aaf** | application/octet-stream | -
|
||||
**.msg** | application/vnd.ms-outlook | -
|
||||
**.xls** | application/vnd.ms-excel | application/msexcel
|
||||
**.pub** | application/vnd.ms-publisher | -
|
||||
**.ppt** | application/vnd.ms-powerpoint | application/mspowerpoint
|
||||
**.doc** | application/msword | application/vnd.ms-word
|
||||
**.ps** | application/postscript | -
|
||||
**.psd** | image/vnd.adobe.photoshop | image/x-psd, application/photoshop
|
||||
**.p7s** | application/pkcs7-signature | -
|
||||
**.ogg** | application/ogg | application/x-ogg
|
||||
**.oga** | audio/ogg | -
|
||||
**.ogv** | video/ogg | -
|
||||
**.png** | image/png | -
|
||||
**.png** | image/vnd.mozilla.apng | -
|
||||
**.jpg** | image/jpeg | -
|
||||
**.jxl** | image/jxl | -
|
||||
**.jp2** | image/jp2 | -
|
||||
**.jpf** | image/jpx | -
|
||||
**.jpm** | image/jpm | video/jpm
|
||||
**.jxs** | image/jxs | -
|
||||
**.gif** | image/gif | -
|
||||
**.webp** | image/webp | -
|
||||
**.exe** | application/vnd.microsoft.portable-executable | -
|
||||
**n/a** | application/x-elf | -
|
||||
**n/a** | application/x-object | -
|
||||
**n/a** | application/x-executable | -
|
||||
**.so** | application/x-sharedlib | -
|
||||
**n/a** | application/x-coredump | -
|
||||
**.a** | application/x-archive | application/x-unix-archive
|
||||
**.deb** | application/vnd.debian.binary-package | -
|
||||
**.tar** | application/x-tar | -
|
||||
**.xar** | application/x-xar | -
|
||||
**.bz2** | application/x-bzip2 | -
|
||||
**.fits** | application/fits | -
|
||||
**.tiff** | image/tiff | -
|
||||
**.bmp** | image/bmp | image/x-bmp, image/x-ms-bmp
|
||||
**.ico** | image/x-icon | -
|
||||
**.mp3** | audio/mpeg | audio/x-mpeg, audio/mp3
|
||||
**.flac** | audio/flac | -
|
||||
**.midi** | audio/midi | audio/mid, audio/sp-midi, audio/x-mid, audio/x-midi
|
||||
**.ape** | audio/ape | -
|
||||
**.mpc** | audio/musepack | -
|
||||
**.amr** | audio/amr | audio/amr-nb
|
||||
**.wav** | audio/wav | audio/x-wav, audio/vnd.wave, audio/wave
|
||||
**.aiff** | audio/aiff | audio/x-aiff
|
||||
**.au** | audio/basic | -
|
||||
**.mpeg** | video/mpeg | -
|
||||
**.mov** | video/quicktime | -
|
||||
**.mqv** | video/quicktime | -
|
||||
**.mp4** | video/mp4 | -
|
||||
**.webm** | video/webm | audio/webm
|
||||
**.3gp** | video/3gpp | video/3gp, audio/3gpp
|
||||
**.3g2** | video/3gpp2 | video/3g2, audio/3gpp2
|
||||
**.avi** | video/x-msvideo | video/avi, video/msvideo
|
||||
**.flv** | video/x-flv | -
|
||||
**.mkv** | video/x-matroska | -
|
||||
**.asf** | video/x-ms-asf | video/asf, video/x-ms-wmv
|
||||
**.aac** | audio/aac | -
|
||||
**.voc** | audio/x-unknown | -
|
||||
**.mp4** | audio/mp4 | audio/x-m4a, audio/x-mp4a
|
||||
**.m4a** | audio/x-m4a | -
|
||||
**.m3u** | application/vnd.apple.mpegurl | audio/mpegurl
|
||||
**.m4v** | video/x-m4v | -
|
||||
**.rmvb** | application/vnd.rn-realmedia-vbr | -
|
||||
**.gz** | application/gzip | application/x-gzip, application/x-gunzip, application/gzipped, application/gzip-compressed, application/x-gzip-compressed, gzip/document
|
||||
**.class** | application/x-java-applet | -
|
||||
**.swf** | application/x-shockwave-flash | -
|
||||
**.crx** | application/x-chrome-extension | -
|
||||
**.ttf** | font/ttf | font/sfnt, application/x-font-ttf, application/font-sfnt
|
||||
**.woff** | font/woff | -
|
||||
**.woff2** | font/woff2 | -
|
||||
**.otf** | font/otf | -
|
||||
**.ttc** | font/collection | -
|
||||
**.eot** | application/vnd.ms-fontobject | -
|
||||
**.wasm** | application/wasm | -
|
||||
**.shx** | application/vnd.shx | -
|
||||
**.shp** | application/vnd.shp | -
|
||||
**.dbf** | application/x-dbf | -
|
||||
**.dcm** | application/dicom | -
|
||||
**.rar** | application/x-rar-compressed | application/x-rar
|
||||
**.djvu** | image/vnd.djvu | -
|
||||
**.mobi** | application/x-mobipocket-ebook | -
|
||||
**.lit** | application/x-ms-reader | -
|
||||
**.bpg** | image/bpg | -
|
||||
**.sqlite** | application/vnd.sqlite3 | application/x-sqlite3
|
||||
**.dwg** | image/vnd.dwg | image/x-dwg, application/acad, application/x-acad, application/autocad_dwg, application/dwg, application/x-dwg, application/x-autocad, drawing/dwg
|
||||
**.nes** | application/vnd.nintendo.snes.rom | -
|
||||
**.lnk** | application/x-ms-shortcut | -
|
||||
**.macho** | application/x-mach-binary | -
|
||||
**.qcp** | audio/qcelp | -
|
||||
**.icns** | image/x-icns | -
|
||||
**.heic** | image/heic | -
|
||||
**.heic** | image/heic-sequence | -
|
||||
**.heif** | image/heif | -
|
||||
**.heif** | image/heif-sequence | -
|
||||
**.hdr** | image/vnd.radiance | -
|
||||
**.mrc** | application/marc | -
|
||||
**.mdb** | application/x-msaccess | -
|
||||
**.accdb** | application/x-msaccess | -
|
||||
**.zst** | application/zstd | -
|
||||
**.cab** | application/vnd.ms-cab-compressed | -
|
||||
**.rpm** | application/x-rpm | -
|
||||
**.xz** | application/x-xz | -
|
||||
**.lz** | application/lzip | application/x-lzip
|
||||
**.torrent** | application/x-bittorrent | -
|
||||
**.cpio** | application/x-cpio | -
|
||||
**n/a** | application/tzif | -
|
||||
**.xcf** | image/x-xcf | -
|
||||
**.pat** | image/x-gimp-pat | -
|
||||
**.gbr** | image/x-gimp-gbr | -
|
||||
**.glb** | model/gltf-binary | -
|
||||
**.avif** | image/avif | -
|
||||
**.cab** | application/x-installshield | -
|
||||
**.jxr** | image/jxr | image/vnd.ms-photo
|
||||
**.txt** | text/plain | -
|
||||
**.html** | text/html | -
|
||||
**.svg** | image/svg+xml | -
|
||||
**.xml** | text/xml | -
|
||||
**.rss** | application/rss+xml | text/rss
|
||||
**.atom** | application/atom+xml | -
|
||||
**.x3d** | model/x3d+xml | -
|
||||
**.kml** | application/vnd.google-earth.kml+xml | -
|
||||
**.xlf** | application/x-xliff+xml | -
|
||||
**.dae** | model/vnd.collada+xml | -
|
||||
**.gml** | application/gml+xml | -
|
||||
**.gpx** | application/gpx+xml | -
|
||||
**.tcx** | application/vnd.garmin.tcx+xml | -
|
||||
**.amf** | application/x-amf | -
|
||||
**.3mf** | application/vnd.ms-package.3dmanufacturing-3dmodel+xml | -
|
||||
**.xfdf** | application/vnd.adobe.xfdf | -
|
||||
**.owl** | application/owl+xml | -
|
||||
**.php** | text/x-php | -
|
||||
**.js** | application/javascript | application/x-javascript, text/javascript
|
||||
**.lua** | text/x-lua | -
|
||||
**.pl** | text/x-perl | -
|
||||
**.py** | text/x-python | text/x-script.python, application/x-python
|
||||
**.json** | application/json | -
|
||||
**.geojson** | application/geo+json | -
|
||||
**.har** | application/json | -
|
||||
**.ndjson** | application/x-ndjson | -
|
||||
**.rtf** | text/rtf | -
|
||||
**.srt** | application/x-subrip | application/x-srt, text/x-srt
|
||||
**.tcl** | text/x-tcl | application/x-tcl
|
||||
**.csv** | text/csv | -
|
||||
**.tsv** | text/tab-separated-values | -
|
||||
**.vcf** | text/vcard | -
|
||||
**.ics** | text/calendar | -
|
||||
**.warc** | application/warc | -
|
||||
**.vtt** | text/vtt | -
|
||||
@ -0,0 +1,260 @@
|
||||
package mimetype
|
||||
|
||||
import (
|
||||
"sync"
|
||||
|
||||
"github.com/gabriel-vasile/mimetype/internal/magic"
|
||||
)
|
||||
|
||||
// mimetype stores the list of MIME types in a tree structure with
|
||||
// "application/octet-stream" at the root of the hierarchy. The hierarchy
|
||||
// approach minimizes the number of checks that need to be done on the input
|
||||
// and allows for more precise results once the base type of file has been
|
||||
// identified.
|
||||
//
|
||||
// root is a detector which passes for any slice of bytes.
|
||||
// When a detector passes the check, the children detectors
|
||||
// are tried in order to find a more accurate MIME type.
|
||||
var root = newMIME("application/octet-stream", "",
|
||||
func([]byte, uint32) bool { return true },
|
||||
xpm, sevenZ, zip, pdf, fdf, ole, ps, psd, p7s, ogg, png, jpg, jxl, jp2, jpx,
|
||||
jpm, jxs, gif, webp, exe, elf, ar, tar, xar, bz2, fits, tiff, bmp, ico, mp3, flac,
|
||||
midi, ape, musePack, amr, wav, aiff, au, mpeg, quickTime, mqv, mp4, webM,
|
||||
threeGP, threeG2, avi, flv, mkv, asf, aac, voc, aMp4, m4a, m3u, m4v, rmvb,
|
||||
gzip, class, swf, crx, ttf, woff, woff2, otf, ttc, eot, wasm, shx, dbf, dcm, rar,
|
||||
djvu, mobi, lit, bpg, sqlite3, dwg, nes, lnk, macho, qcp, icns, heic,
|
||||
heicSeq, heif, heifSeq, hdr, mrc, mdb, accdb, zstd, cab, rpm, xz, lzip,
|
||||
torrent, cpio, tzif, xcf, pat, gbr, glb, avif, cabIS, jxr,
|
||||
// Keep text last because it is the slowest check
|
||||
text,
|
||||
)
|
||||
|
||||
// errMIME is returned from Detect functions when err is not nil.
|
||||
// Detect could return root for erroneous cases, but it needs to lock mu in order to do so.
|
||||
// errMIME is same as root but it does not require locking.
|
||||
var errMIME = newMIME("application/octet-stream", "", func([]byte, uint32) bool { return false })
|
||||
|
||||
// mu guards access to the root MIME tree. Access to root must be synchronized with this lock.
|
||||
var mu = &sync.RWMutex{}
|
||||
|
||||
// The list of nodes appended to the root node.
|
||||
var (
|
||||
xz = newMIME("application/x-xz", ".xz", magic.Xz)
|
||||
gzip = newMIME("application/gzip", ".gz", magic.Gzip).alias(
|
||||
"application/x-gzip", "application/x-gunzip", "application/gzipped",
|
||||
"application/gzip-compressed", "application/x-gzip-compressed",
|
||||
"gzip/document")
|
||||
sevenZ = newMIME("application/x-7z-compressed", ".7z", magic.SevenZ)
|
||||
zip = newMIME("application/zip", ".zip", magic.Zip, xlsx, docx, pptx, epub, jar, odt, ods, odp, odg, odf, odc, sxc).
|
||||
alias("application/x-zip", "application/x-zip-compressed")
|
||||
tar = newMIME("application/x-tar", ".tar", magic.Tar)
|
||||
xar = newMIME("application/x-xar", ".xar", magic.Xar)
|
||||
bz2 = newMIME("application/x-bzip2", ".bz2", magic.Bz2)
|
||||
pdf = newMIME("application/pdf", ".pdf", magic.Pdf).
|
||||
alias("application/x-pdf")
|
||||
fdf = newMIME("application/vnd.fdf", ".fdf", magic.Fdf)
|
||||
xlsx = newMIME("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", ".xlsx", magic.Xlsx)
|
||||
docx = newMIME("application/vnd.openxmlformats-officedocument.wordprocessingml.document", ".docx", magic.Docx)
|
||||
pptx = newMIME("application/vnd.openxmlformats-officedocument.presentationml.presentation", ".pptx", magic.Pptx)
|
||||
epub = newMIME("application/epub+zip", ".epub", magic.Epub)
|
||||
jar = newMIME("application/jar", ".jar", magic.Jar)
|
||||
ole = newMIME("application/x-ole-storage", "", magic.Ole, msi, aaf, msg, xls, pub, ppt, doc)
|
||||
msi = newMIME("application/x-ms-installer", ".msi", magic.Msi).
|
||||
alias("application/x-windows-installer", "application/x-msi")
|
||||
aaf = newMIME("application/octet-stream", ".aaf", magic.Aaf)
|
||||
doc = newMIME("application/msword", ".doc", magic.Doc).
|
||||
alias("application/vnd.ms-word")
|
||||
ppt = newMIME("application/vnd.ms-powerpoint", ".ppt", magic.Ppt).
|
||||
alias("application/mspowerpoint")
|
||||
pub = newMIME("application/vnd.ms-publisher", ".pub", magic.Pub)
|
||||
xls = newMIME("application/vnd.ms-excel", ".xls", magic.Xls).
|
||||
alias("application/msexcel")
|
||||
msg = newMIME("application/vnd.ms-outlook", ".msg", magic.Msg)
|
||||
ps = newMIME("application/postscript", ".ps", magic.Ps)
|
||||
fits = newMIME("application/fits", ".fits", magic.Fits)
|
||||
ogg = newMIME("application/ogg", ".ogg", magic.Ogg, oggAudio, oggVideo).
|
||||
alias("application/x-ogg")
|
||||
oggAudio = newMIME("audio/ogg", ".oga", magic.OggAudio)
|
||||
oggVideo = newMIME("video/ogg", ".ogv", magic.OggVideo)
|
||||
text = newMIME("text/plain", ".txt", magic.Text, html, svg, xml, php, js, lua, perl, python, json, ndJSON, rtf, srt, tcl, csv, tsv, vCard, iCalendar, warc, vtt)
|
||||
xml = newMIME("text/xml", ".xml", magic.XML, rss, atom, x3d, kml, xliff, collada, gml, gpx, tcx, amf, threemf, xfdf, owl2)
|
||||
json = newMIME("application/json", ".json", magic.JSON, geoJSON, har)
|
||||
har = newMIME("application/json", ".har", magic.HAR)
|
||||
csv = newMIME("text/csv", ".csv", magic.Csv)
|
||||
tsv = newMIME("text/tab-separated-values", ".tsv", magic.Tsv)
|
||||
geoJSON = newMIME("application/geo+json", ".geojson", magic.GeoJSON)
|
||||
ndJSON = newMIME("application/x-ndjson", ".ndjson", magic.NdJSON)
|
||||
html = newMIME("text/html", ".html", magic.HTML)
|
||||
php = newMIME("text/x-php", ".php", magic.Php)
|
||||
rtf = newMIME("text/rtf", ".rtf", magic.Rtf)
|
||||
js = newMIME("application/javascript", ".js", magic.Js).
|
||||
alias("application/x-javascript", "text/javascript")
|
||||
srt = newMIME("application/x-subrip", ".srt", magic.Srt).
|
||||
alias("application/x-srt", "text/x-srt")
|
||||
vtt = newMIME("text/vtt", ".vtt", magic.Vtt)
|
||||
lua = newMIME("text/x-lua", ".lua", magic.Lua)
|
||||
perl = newMIME("text/x-perl", ".pl", magic.Perl)
|
||||
python = newMIME("text/x-python", ".py", magic.Python).
|
||||
alias("text/x-script.python", "application/x-python")
|
||||
tcl = newMIME("text/x-tcl", ".tcl", magic.Tcl).
|
||||
alias("application/x-tcl")
|
||||
vCard = newMIME("text/vcard", ".vcf", magic.VCard)
|
||||
iCalendar = newMIME("text/calendar", ".ics", magic.ICalendar)
|
||||
svg = newMIME("image/svg+xml", ".svg", magic.Svg)
|
||||
rss = newMIME("application/rss+xml", ".rss", magic.Rss).
|
||||
alias("text/rss")
|
||||
owl2 = newMIME("application/owl+xml", ".owl", magic.Owl2)
|
||||
atom = newMIME("application/atom+xml", ".atom", magic.Atom)
|
||||
x3d = newMIME("model/x3d+xml", ".x3d", magic.X3d)
|
||||
kml = newMIME("application/vnd.google-earth.kml+xml", ".kml", magic.Kml)
|
||||
xliff = newMIME("application/x-xliff+xml", ".xlf", magic.Xliff)
|
||||
collada = newMIME("model/vnd.collada+xml", ".dae", magic.Collada)
|
||||
gml = newMIME("application/gml+xml", ".gml", magic.Gml)
|
||||
gpx = newMIME("application/gpx+xml", ".gpx", magic.Gpx)
|
||||
tcx = newMIME("application/vnd.garmin.tcx+xml", ".tcx", magic.Tcx)
|
||||
amf = newMIME("application/x-amf", ".amf", magic.Amf)
|
||||
threemf = newMIME("application/vnd.ms-package.3dmanufacturing-3dmodel+xml", ".3mf", magic.Threemf)
|
||||
png = newMIME("image/png", ".png", magic.Png, apng)
|
||||
apng = newMIME("image/vnd.mozilla.apng", ".png", magic.Apng)
|
||||
jpg = newMIME("image/jpeg", ".jpg", magic.Jpg)
|
||||
jxl = newMIME("image/jxl", ".jxl", magic.Jxl)
|
||||
jp2 = newMIME("image/jp2", ".jp2", magic.Jp2)
|
||||
jpx = newMIME("image/jpx", ".jpf", magic.Jpx)
|
||||
jpm = newMIME("image/jpm", ".jpm", magic.Jpm).
|
||||
alias("video/jpm")
|
||||
jxs = newMIME("image/jxs", ".jxs", magic.Jxs)
|
||||
xpm = newMIME("image/x-xpixmap", ".xpm", magic.Xpm)
|
||||
bpg = newMIME("image/bpg", ".bpg", magic.Bpg)
|
||||
gif = newMIME("image/gif", ".gif", magic.Gif)
|
||||
webp = newMIME("image/webp", ".webp", magic.Webp)
|
||||
tiff = newMIME("image/tiff", ".tiff", magic.Tiff)
|
||||
bmp = newMIME("image/bmp", ".bmp", magic.Bmp).
|
||||
alias("image/x-bmp", "image/x-ms-bmp")
|
||||
ico = newMIME("image/x-icon", ".ico", magic.Ico)
|
||||
icns = newMIME("image/x-icns", ".icns", magic.Icns)
|
||||
psd = newMIME("image/vnd.adobe.photoshop", ".psd", magic.Psd).
|
||||
alias("image/x-psd", "application/photoshop")
|
||||
heic = newMIME("image/heic", ".heic", magic.Heic)
|
||||
heicSeq = newMIME("image/heic-sequence", ".heic", magic.HeicSequence)
|
||||
heif = newMIME("image/heif", ".heif", magic.Heif)
|
||||
heifSeq = newMIME("image/heif-sequence", ".heif", magic.HeifSequence)
|
||||
hdr = newMIME("image/vnd.radiance", ".hdr", magic.Hdr)
|
||||
avif = newMIME("image/avif", ".avif", magic.AVIF)
|
||||
mp3 = newMIME("audio/mpeg", ".mp3", magic.Mp3).
|
||||
alias("audio/x-mpeg", "audio/mp3")
|
||||
flac = newMIME("audio/flac", ".flac", magic.Flac)
|
||||
midi = newMIME("audio/midi", ".midi", magic.Midi).
|
||||
alias("audio/mid", "audio/sp-midi", "audio/x-mid", "audio/x-midi")
|
||||
ape = newMIME("audio/ape", ".ape", magic.Ape)
|
||||
musePack = newMIME("audio/musepack", ".mpc", magic.MusePack)
|
||||
wav = newMIME("audio/wav", ".wav", magic.Wav).
|
||||
alias("audio/x-wav", "audio/vnd.wave", "audio/wave")
|
||||
aiff = newMIME("audio/aiff", ".aiff", magic.Aiff).alias("audio/x-aiff")
|
||||
au = newMIME("audio/basic", ".au", magic.Au)
|
||||
amr = newMIME("audio/amr", ".amr", magic.Amr).
|
||||
alias("audio/amr-nb")
|
||||
aac = newMIME("audio/aac", ".aac", magic.AAC)
|
||||
voc = newMIME("audio/x-unknown", ".voc", magic.Voc)
|
||||
aMp4 = newMIME("audio/mp4", ".mp4", magic.AMp4).
|
||||
alias("audio/x-m4a", "audio/x-mp4a")
|
||||
m4a = newMIME("audio/x-m4a", ".m4a", magic.M4a)
|
||||
m3u = newMIME("application/vnd.apple.mpegurl", ".m3u", magic.M3u).
|
||||
alias("audio/mpegurl")
|
||||
m4v = newMIME("video/x-m4v", ".m4v", magic.M4v)
|
||||
mp4 = newMIME("video/mp4", ".mp4", magic.Mp4)
|
||||
webM = newMIME("video/webm", ".webm", magic.WebM).
|
||||
alias("audio/webm")
|
||||
mpeg = newMIME("video/mpeg", ".mpeg", magic.Mpeg)
|
||||
quickTime = newMIME("video/quicktime", ".mov", magic.QuickTime)
|
||||
mqv = newMIME("video/quicktime", ".mqv", magic.Mqv)
|
||||
threeGP = newMIME("video/3gpp", ".3gp", magic.ThreeGP).
|
||||
alias("video/3gp", "audio/3gpp")
|
||||
threeG2 = newMIME("video/3gpp2", ".3g2", magic.ThreeG2).
|
||||
alias("video/3g2", "audio/3gpp2")
|
||||
avi = newMIME("video/x-msvideo", ".avi", magic.Avi).
|
||||
alias("video/avi", "video/msvideo")
|
||||
flv = newMIME("video/x-flv", ".flv", magic.Flv)
|
||||
mkv = newMIME("video/x-matroska", ".mkv", magic.Mkv)
|
||||
asf = newMIME("video/x-ms-asf", ".asf", magic.Asf).
|
||||
alias("video/asf", "video/x-ms-wmv")
|
||||
rmvb = newMIME("application/vnd.rn-realmedia-vbr", ".rmvb", magic.Rmvb)
|
||||
class = newMIME("application/x-java-applet", ".class", magic.Class)
|
||||
swf = newMIME("application/x-shockwave-flash", ".swf", magic.SWF)
|
||||
crx = newMIME("application/x-chrome-extension", ".crx", magic.CRX)
|
||||
ttf = newMIME("font/ttf", ".ttf", magic.Ttf).
|
||||
alias("font/sfnt", "application/x-font-ttf", "application/font-sfnt")
|
||||
woff = newMIME("font/woff", ".woff", magic.Woff)
|
||||
woff2 = newMIME("font/woff2", ".woff2", magic.Woff2)
|
||||
otf = newMIME("font/otf", ".otf", magic.Otf)
|
||||
ttc = newMIME("font/collection", ".ttc", magic.Ttc)
|
||||
eot = newMIME("application/vnd.ms-fontobject", ".eot", magic.Eot)
|
||||
wasm = newMIME("application/wasm", ".wasm", magic.Wasm)
|
||||
shp = newMIME("application/vnd.shp", ".shp", magic.Shp)
|
||||
shx = newMIME("application/vnd.shx", ".shx", magic.Shx, shp)
|
||||
dbf = newMIME("application/x-dbf", ".dbf", magic.Dbf)
|
||||
exe = newMIME("application/vnd.microsoft.portable-executable", ".exe", magic.Exe)
|
||||
elf = newMIME("application/x-elf", "", magic.Elf, elfObj, elfExe, elfLib, elfDump)
|
||||
elfObj = newMIME("application/x-object", "", magic.ElfObj)
|
||||
elfExe = newMIME("application/x-executable", "", magic.ElfExe)
|
||||
elfLib = newMIME("application/x-sharedlib", ".so", magic.ElfLib)
|
||||
elfDump = newMIME("application/x-coredump", "", magic.ElfDump)
|
||||
ar = newMIME("application/x-archive", ".a", magic.Ar, deb).
|
||||
alias("application/x-unix-archive")
|
||||
deb = newMIME("application/vnd.debian.binary-package", ".deb", magic.Deb)
|
||||
rpm = newMIME("application/x-rpm", ".rpm", magic.RPM)
|
||||
dcm = newMIME("application/dicom", ".dcm", magic.Dcm)
|
||||
odt = newMIME("application/vnd.oasis.opendocument.text", ".odt", magic.Odt, ott).
|
||||
alias("application/x-vnd.oasis.opendocument.text")
|
||||
ott = newMIME("application/vnd.oasis.opendocument.text-template", ".ott", magic.Ott).
|
||||
alias("application/x-vnd.oasis.opendocument.text-template")
|
||||
ods = newMIME("application/vnd.oasis.opendocument.spreadsheet", ".ods", magic.Ods, ots).
|
||||
alias("application/x-vnd.oasis.opendocument.spreadsheet")
|
||||
ots = newMIME("application/vnd.oasis.opendocument.spreadsheet-template", ".ots", magic.Ots).
|
||||
alias("application/x-vnd.oasis.opendocument.spreadsheet-template")
|
||||
odp = newMIME("application/vnd.oasis.opendocument.presentation", ".odp", magic.Odp, otp).
|
||||
alias("application/x-vnd.oasis.opendocument.presentation")
|
||||
otp = newMIME("application/vnd.oasis.opendocument.presentation-template", ".otp", magic.Otp).
|
||||
alias("application/x-vnd.oasis.opendocument.presentation-template")
|
||||
odg = newMIME("application/vnd.oasis.opendocument.graphics", ".odg", magic.Odg, otg).
|
||||
alias("application/x-vnd.oasis.opendocument.graphics")
|
||||
otg = newMIME("application/vnd.oasis.opendocument.graphics-template", ".otg", magic.Otg).
|
||||
alias("application/x-vnd.oasis.opendocument.graphics-template")
|
||||
odf = newMIME("application/vnd.oasis.opendocument.formula", ".odf", magic.Odf).
|
||||
alias("application/x-vnd.oasis.opendocument.formula")
|
||||
odc = newMIME("application/vnd.oasis.opendocument.chart", ".odc", magic.Odc).
|
||||
alias("application/x-vnd.oasis.opendocument.chart")
|
||||
sxc = newMIME("application/vnd.sun.xml.calc", ".sxc", magic.Sxc)
|
||||
rar = newMIME("application/x-rar-compressed", ".rar", magic.RAR).
|
||||
alias("application/x-rar")
|
||||
djvu = newMIME("image/vnd.djvu", ".djvu", magic.DjVu)
|
||||
mobi = newMIME("application/x-mobipocket-ebook", ".mobi", magic.Mobi)
|
||||
lit = newMIME("application/x-ms-reader", ".lit", magic.Lit)
|
||||
sqlite3 = newMIME("application/vnd.sqlite3", ".sqlite", magic.Sqlite).
|
||||
alias("application/x-sqlite3")
|
||||
dwg = newMIME("image/vnd.dwg", ".dwg", magic.Dwg).
|
||||
alias("image/x-dwg", "application/acad", "application/x-acad",
|
||||
"application/autocad_dwg", "application/dwg", "application/x-dwg",
|
||||
"application/x-autocad", "drawing/dwg")
|
||||
warc = newMIME("application/warc", ".warc", magic.Warc)
|
||||
nes = newMIME("application/vnd.nintendo.snes.rom", ".nes", magic.Nes)
|
||||
lnk = newMIME("application/x-ms-shortcut", ".lnk", magic.Lnk)
|
||||
macho = newMIME("application/x-mach-binary", ".macho", magic.MachO)
|
||||
qcp = newMIME("audio/qcelp", ".qcp", magic.Qcp)
|
||||
mrc = newMIME("application/marc", ".mrc", magic.Marc)
|
||||
mdb = newMIME("application/x-msaccess", ".mdb", magic.MsAccessMdb)
|
||||
accdb = newMIME("application/x-msaccess", ".accdb", magic.MsAccessAce)
|
||||
zstd = newMIME("application/zstd", ".zst", magic.Zstd)
|
||||
cab = newMIME("application/vnd.ms-cab-compressed", ".cab", magic.Cab)
|
||||
cabIS = newMIME("application/x-installshield", ".cab", magic.InstallShieldCab)
|
||||
lzip = newMIME("application/lzip", ".lz", magic.Lzip).alias("application/x-lzip")
|
||||
torrent = newMIME("application/x-bittorrent", ".torrent", magic.Torrent)
|
||||
cpio = newMIME("application/x-cpio", ".cpio", magic.Cpio)
|
||||
tzif = newMIME("application/tzif", "", magic.TzIf)
|
||||
p7s = newMIME("application/pkcs7-signature", ".p7s", magic.P7s)
|
||||
xcf = newMIME("image/x-xcf", ".xcf", magic.Xcf)
|
||||
pat = newMIME("image/x-gimp-pat", ".pat", magic.Pat)
|
||||
gbr = newMIME("image/x-gimp-gbr", ".gbr", magic.Gbr)
|
||||
xfdf = newMIME("application/vnd.adobe.xfdf", ".xfdf", magic.Xfdf)
|
||||
glb = newMIME("model/gltf-binary", ".glb", magic.Glb)
|
||||
jxr = newMIME("image/jxr", ".jxr", magic.Jxr).alias("image/vnd.ms-photo")
|
||||
)
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue